Webmaster's Note: The whole dataset is available Here. Please download the dataset instead of crawling the website.
Basic Info:
id: J86-3001
title: Attention Intentions And The Structure Of Discourse
venue: CL
year: 1986
pdf: link
title: Attention Intentions And The Structure Of Discourse
venue: CL
year: 1986
pdf: link
Abstract
state, being dynamic, records the objects, properties, and relations that are salient at each point of the discourse. The distinction among these components is essential to provide an adequate explanation of such discourse phenomena as cue phrases, referring expressions, and interruptions. The theory of attention, intention, and aggregation of utterances is illustrated in the paper with a number of example discourses. Various properties of discourse are described, and explanations for the behavior of cue phrases, referring expressions, and interruptions are explored. This theory provides a framework for describing the processing of utterances in a discourse. Discourse processing requires recognizing how the utterances of the discourse aggregate into segments, recognizing the intentions expressed in the discourse and the relationships among intentions, and track- ing the discourse through the operation of the mechanisms associated with attentional state. This processing description specifies in these recognition tasks the role of information from the discourse and from the participants' knowledge of the domain.
| Stat | Rank | Value |
|---|---|---|
| Incoming Citations | 3(3) | 332(324) |
| Outgoing Citations | 2997(3811) | 6(4) |
| PageRank | 6 | 6636 |
| PageRank per Year | 8 | 301.63 |
| By Title |
|---|
| By Abstract |
|---|
| By Full Text |
|---|
| By Co-citation |
|---|
| Citing sentences |
|---|
| W98-1125 1 198:336 This, however, appears to run counter to what we expect from results reported in prior work on discourse(Kurohashi and Nagao, 1994; Litman and Passonneau, 1995; Grosz and Sidner, 1986; Marcu, 1997), where the notion of clues or cue phrases forms an important part of identifying a structure of discourse7 Table 4 shows how the confidence value (CF) affects the performance of discourse models. |
| W04-0211 2 16:230 2 The assignment of correct temporal, personal and spatial interpretation to utterances, which relies in large part on the relative location of referential expression and their 2 Complex default logic based reasoning as in Structured Discourse Representation Theory (Asher 1993; Asher and Lascarides 2003), speculations about the intentions or beliefs of speakers (as in Grosz and Sidner (1986)), or the intricate node labeling exercises familiar from Rhetorical Structure Theory (Mann and Thompson 1988; Marcu 1999, 2000) are not necessary. |
| P89-1025 3 10:203 In their work on discourse analysis, Grosz and Sidner (1986) argue that it is necessary to represent the intentional structure, the attentional structure (knowledge about which aspects of a dialogue are in focus at each point), and the linguistic structure of "The research described in this paper was supported by the Defense Advanced Research Projects Agency (DARPA) under a NASA Ames cooperative agreement number NCC 2-520. |
| P89-1025 4 24:203 We have developed a text planner that records the following information about the responses it produces: the information that Grosz and Sidner (1986) have presented as the basics of a discourse structure: intentional structure: a representation of the effect each part of the text is intended to have on the hearer and how the complete text achieves the overall discourse purpose (e.g. , describe entity, persuade hearer to perform an action). |
| W93-0236 5 2:80 As is argued for in Van Kuppevelt (1993), this alternative not only implies uniformity on the structural levels involved, i.e. the linguistic and intentional level, but also on the level of attentional states (Grosz and Sidner 1986). |
| W97-0402 6 17:173 reflect embedding subdialogues (Grosz and Sidner 1986). |
| W03-2121 7 9:128 There are several overtly declarative theories of the structure of such texts (many of them stemming from the work of Mann and Thompson (1988) and Grosz and Sidner (1986)), and several models of text generation and text interpretation which make reference to these declarative theories (see e.g. Hovy (1993) and Marcu (2000) for a summary of generation and in- terpretation methods respectively). |
| P02-1012 8 28:175 Since discourse anaphora resolution was first studied theoretically (Grosz, 1977; Webber, 1979; Sidner, 1983; Grosz and Sidner, 1986), it has come to be dominated by Centering Theory (Grosz et al. , 1995; Di Eugenio, 1998; Walker, 1998) which proposes rules for the determination of focus and salience within a given segment of discourse. |
| P02-1012 9 10:175 Almost without exception, they focus on anaphoric pronouns as described in Focus/Centering Theory (Webber, 1979; Sidner, 1983; Grosz and Sidner, 1986; Walker, 1998), ignoring the multitude of other possible types. |
| P97-1013 10 9:221 On the other hand, although the theories described by Grosz and Sidner (1986), Polanyi (1988), and Mann and Thompson (1988) are successfully applied manually, they,are too informal to support an automatic approach to discourse analysis. |
| P97-1013 11 32:221 Such constructs can include tense 96 and aspect (Moens and Steedman, 1988; Webber, 1988; Lascarides and Asher, 1993), certain patterns of pronominalization and anaphoric usages (Sidner, 1981; Grosz and Sidner, 1986; Sumita et al. , 1992; Grosz, Joshi, and Weinstein, 1995),/t-clefts (Delin and Oberlander, 1992), and discourse markers or cue phrases (Ballard, Conrad, and Longacre, 1971; Halliday and Hasan, 1976; Van Dijk, 1979; Longacre, 1983; Grosz and Sidner, 1986; Schiffrin, 1987; Cohen, 1987; Redeker, 1990; Sanders, Spooren, and Noordman, 1992; Hirschberg and Litman, 1993; Knott, 1995; Fraser, 1996; Moser and Moore, 1997). |
| P97-1013 12 57:221 3 A corpus analysis of discourse markers 3.1 Materials We used previous work on cue phrases (Halliday and Hasan, 1976; Grosz and Sidner, 1986; Martin, 1992; Hirschberg and Litman, 1993; Knott, 1995; Fraser, 1996) to create an initial set of more than 450 potential discourse markers. |
| P99-1046 13 31:199 Discourse segmentation, on the other hand, is often finer-grained, and focuses on identifying relations between utterances (e.g. Grosz and Sidner, 1986 or Hirschberg and Grosz, 1992). |
| P04-1019 14 5:183 Work such as (Poesio et al. , 1998; Poesio et al. , 2002; Poesio, 2003) provided an experimental confirmation of the hypothesis first put forward by Sidner (1979) that BRIDGING DESCRIPTIONS (BD)1 are more similar to pronouns than to other types of definite descriptions, in that they are sensitive to the local rather than the global focus (Grosz and Sidner, 1986). |
| P04-1019 15 48:183 2.2 Salience One of the motivations behind Grosz and Sidners (1986) distinction between two aspects of the attentional state the LOCAL FOCUS and the GLOBAL FOCUSis the difference between the interpretive preferences of pronouns and definite descriptions. |
| P93-1041 16 21:85 (Grosz and Sidner, 1986) However, such clues are not directly based on coherence which forms the clauses or sentences into a segment. |
| A00-1008 17 115:277 5.2 Structure of human tutorial dialogues In an earlier analysis (Kim, Freedman and Evens 1998) we showed that a significant portion of human-human tutorial dialogues can be modeled with the hierarchical structure o f task-oriented dialogues (Grosz and Sidner 1986). |
| A00-1008 18 38:277 Third, our dialogues are task-oriented and have a hierarchical structure (Grosz and Sidner 1986). |
| J89-2001 19 151:770 Grosz and Sidner (Grosz et al. 1986) and Reichman (1984) have investigated discourse structure and have shown that a coherent discourse can be segmented into units that have well-defined relationships to one another. |
| J00-3005 20 39:943 On the other hand, the theories aimed at characterizing the constraints that pertain to the structure of unrestricted texts and the computational mechanisms that would enable the derivation of these structures (van Dijk 1972; Zock 1985; Grosz and Sidner 1986; Mann and Thompson 1988; Polanyi 1988, 1996; Hobbs 1990) are either too informal or incompletely specified to support a fully automatic approach to discourse analysis. |
| J00-3005 21 137:943 And Morris and Hirst (1991) have also shown that there is a correlation between cohesion-defined textual segments and hierarchical, intentionally defined segments (Grosz and Sidner 1986). |
| J00-3005 22 189:943 405 Computational Linguistics Volume 26, Number 3 3.1 Materials Many researchers have published lists of potential discourse markers and cue phrases (Halliday and Hasan 1976; Grosz and Sidner 1986; Martin 1992; Hirschberg and Litman 1993; Knott 1995; Fraser 1996). |
| W06-1408 23 25:197 A context set is defined as the set of the entities the addressee is currently assumed to be attending to this is similar to the concept of focus spaces of the discourse focus stack in Grosz & Sidners (1986) theory of discourse structure. |
| J93-4004 24 77:934 In this approach, the intentional structure describing the speaker's purposes and the relationships between them (Grosz and Sidner 1986) is explicitly represented. |
| J93-4004 25 436:934 They may be used to mark shifts in attentional structure, discourse segment boundaries, or aspects of the exchange structure in interactive discourse (Grosz and Sidner 1986; Redeker 1990; Schiffrin 1987). |
| J93-4004 26 919:934 That is, we must address issues of how to build a representation of the intentional structure of the dialogue that is emerging across conversational turns (Grosz and Sidner 1986) and to track global focus (Grosz 1977). |
| J93-4004 27 858:934 Grosz and Sidner (1986) argue that such relations between intentions are a crucial part of intentional structure. |
| J93-4004 28 160:934 To make clear what is missing, we have represented in Figure 5 the intentional structure of this text using Grosz and Sidner's (1986) notions of dominance and satisfaction-precedence. |
| J93-4004 29 161:934 In Grosz and Sidner's theory (1986, p. 179), if an action that satisfies one intention, h, is intended to provide part of the satisfaction of another intention,/2, then/2 dominates h. h satisfaction-precedes 12 whenever h must be satisfied before/2. |
| W06-1611 30 37:230 2.1 Discourse structure We base our annotation of discourse structure on the Grosz & Sidner theory of discourse structure (Grosz and Sidner, 1986). |
| P98-1090 31 25:162 Unlike Sidner's theory of focus (Sidner, 1979), the theory of the attentional state in (Grosz and Sidner, 1986) (henceforth: G&S) does not include explicit provision for long-distance pronominalisations, although some of the necessary tools are potentially already there, as we will see. |
| P98-1090 32 28:162 2 Theories of focus Space unfortunately prevents a full discussion of Grosz's (1977), Sidner's (1979), and G&S's (1986) theories of focus and the attentional state in this abstract. |
| W06-1320 33 13:156 Following some of the most prominent discourse theories in literature (Grosz and Sidner, 1986; Marcu, 2000), a hierarchical representation of the thematic episodes can be proposed. |
| W96-0109 34 11:285 In the past, the problem has been addressed mostly by computational linguists in relation to issues like coreference (Hobbs, 1978), anaphora resolution (Grosz and Sidner, 1986; Lappin and Leass, 1994), or discourse center (Joshi and Weinstein, 1981; Walker et al. , 1994). |
| C00-2112 35 11:123 This observation plays a key role in Centering Theory (Grosz and Sidner, 1986; Grosz et al. , 1995) and other computational al)t)roaches in which rethrring expressions are resolved by locating their antecedents in the discourse. |
| P06-2051 36 103:250 For this purpose we use discourse segments proposed by Grosz and Sidner (Grosz and Sidner, 1986) to describe the kind of utterances during the interaction. |
| P89-1030 37 6:152 As a discourse progresses, an adequate discourse model must represent the relevant entities, and the relationships between them (Grosz and Sidner, 1986), A speaker may then felicitously refer anaphorically to an object (subject to focusing or centering constraints (Grosz et al. , 1983, Sidner 1981, 1983, Brennan et al. 1987) ) if there is an existing DE representing it, or if a corresponding DE may be directly inferred from an existing DE. |
| W97-1301 38 131:143 A mechanism for focus tracking (Grosz and Sidner, 1986) or a clustering algorithm should be applied first in order to minimise the costs. |
| W93-0237 39 46:58 There are a number of sub-issues related to this focus of concern, all of which tend to lend themselves to a traditional RST approach: Written rather than interactive discourse D A number of studies in the context of interactive discourse have emphasized the need for separate representation of intentions (Fox, 1988; Grosz and Sidner, 1986; Moore and Paris, 1989). |
| W00-1433 40 62:193 One of the criticisms of RST is that there is an infinite set of relations (Grosz and Sidner, 1986). |
| W00-1433 41 180:193 In (1999), Nakatani and Traum describe a hierarchical annotation of dialog for I-units, based on the domination and satisfaction-precedence relations of (Grosz and Sidner, 1986). |
| D08-1035 42 116:228 We are especially interested in cue phrases, which are explicit markers for discourse structure, such as now or first (Grosz and Sidner, 1986; Hirschberg and Litman, 1993; Knott, 1996). |
| D08-1035 43 13:228 For example, consider cue phrases, which are explicit discourse markers such as now or however (Grosz and Sidner, 1986; Hirschberg and Litman, 1993; Knott, 1996). |
| C96-2158 44 10:174 At discourse level, determining the set of admissible antecedents requires a representation which is ordered according to pragmatic relations (Grosz and Sidner, 1986; Wehber, 1989). |
| W00-0402 45 9:208 Results of discourse analysis can be used to solve many important NLP problems such as anaphoric reference (Hirst 1981), tense and aspect analysis (Hwang and Schubert 1992), intention recognition (Grosz and Sidner 1986; Litman and Allen 1990), or'can be directly applied to computational NLP applications such as text abstraction (Ono et al. 1994; T'sou et al. 1996) and text generation (McKeown 1985; Lin et al. 1991). |
| W04-0713 46 118:245 4 The DAR-algorithm 4.1 Search Space and DE lists dar presupposes the discourse structure described by Grosz and Sidner (1986). |
| J94-2006 47 24:375 Other research on discourse (e.g. , Grosz 1981; Grosz and Sidner 1986; Reichman 1978) has studied another phenomenon, the global focus of discourse. |
| J94-2006 48 42:375 Note that because the centering literature claims that centering should operate only within a discourse segment, and because this claim is used to explain some otherwise problematic cases of pronoun use, not being able to adequately handle discourse seg1 Notice that we use the term focusing to cover all local focusing frameworks, Sidner's focusing framework (Sidner 1979), Carter's extensions to Sidner's framework (Carter 1987), the centering framework (Grosz, Joshi, and Weinstein 1983 and others), our framework (RAFT/RAPR), PUNDIT (Dahl \[1986\] and others), etc. We use uppercase ("Focusing," or "Local Focusing"), or "Sidner's Focusing Algorithm/Framework" to refer to Sidner's work. |
| P98-1100 49 22:131 It was reported that the lexical chains closely correlated to the intentional structure (Grosz and Sidner, 1986) of the texts, where the start and end of chains coincided with the intention ranges. |
| E93-1030 50 66:268 Polanyi 1985, Grosz and Sidner 1986, Webber 1991), assuming that it is built in a depth first left to right manner. |
| W93-0240 51 7:52 Thus, on the one hand, our integrative vi(,ws toward discourse structures and intentions are similar to (Grosz and Sidner, 1986) and (Moore a ll(I Pollack, 1992) in the sense that we hold The separation of attentional and intentional "tracks" of discourse \]. |
| W93-0240 52 40:52 This integrative view is similar to others, e.g., (Grosz and Sidner, 1986) and (Moore and Pollack. |
| P08-1097 53 228:232 Richer models of discourseincludehierarchicalstructure(GroszandSidner, 1986) and Rhetorical Structure Theory (Mann and Thompson, 1988). |
| J96-2005 54 85:174 The cache model maintains the distinction between intentional structure and attentional state first proposed by Grosz and Sidner (1986). |
| J96-2005 55 46:174 2 The cue word but in utterance 22a indicates a push, a new intention (Grosz and Sidner 1986). |
| J96-2005 56 6:174 Of all theories based on hierarchical recency, only Grosz and Sidner's theory of discourse structure provides an operationalization of hierarchical recency in terms of their stack model of attentional state (Sidner 1979; Grosz 1977; Grosz and Sidner 1986). |
| C98-1062 57 11:140 Knowledge-based systems as Grosz and Sidner's (1986) require an extensive manual knowledge engineering effort to create the knowledge base (semantic network and/or frames) and this is only possible in very limited and well-known domains. |
| P94-1050 58 18:103 tempted to confirm the theories of discourse structure outlined in (Grosz and Sidner, 1986) using information from a thesaurus. |
| P94-1050 59 8:103 Whether the organization of the text is hierarchical in nature, as described in (Grosz and Sidner, 1986), or linear, as examined in (Skorochod'ko, 1972), boundaries between subtopics will generally exist. |
| P92-1001 60 46:245 Grosz and Sidner 1986:182). |
| P92-1001 61 57:245 Kamp 1981), but goes on to assume with Grosz and Sidner (1986) that candidate discourses possess hierarchical structure, with units linked by discourse relations modelled after those proposed by IIobbs (1979, 1985) (cf. |
| W93-0208 62 2:137 Integrative two-medium work should build on insights and findings in the one-medium disciplines of graphical manipulative interfaces (e.g. , Hutchins et al. , 1986; Sullivan and Tyler, 1991) and natural language discourse (e.g. , Grosz and Sidner, 1986; Litman and Allen, 1987; Hovy, 1988; Lambert and Carberry, 1991; Paris, 1991). |
| C98-2174 63 53:120 The rules of inference are clear candidates for operationalisation: moves such as Modus Ponens are clearly vital components of any argument though, as noted in Grosz and Sidner (1986), p201, it is inappropriate to view the implication step as one of conventional material implication. |
| C98-2174 64 51:120 The roles of these goals and their interrelationships are explored in relation to the informationintention-attention model of Grosz and Sidner (1986) in more detail in Reed and Long (1997a). |
| W99-0108 65 44:260 Here, to distingni~h o~ notion from other notions of discmuse segmentation found in the literature (e.g. , Reidmum (1985) or Grosz & Sidner (1986)), we use the term discomae thread to capture the structuring notion to whidz we refer. |
| W99-0108 66 78:260 Reichman (1985) and Grosz & Sidner (1986) indicate that discourse segmentation has an effect on the linguistic realization of referring expressions. |
| W99-0108 67 50:260 For instance, in the kinds of discourses studied in Grosz & Sidner (1986) the threading device may be the intentional structures (and each of their discourse segments would constitute a thread of the discourse), in the discourses that we studied (New York Times a~cles), threads defined in terms of the time referenced in a clause appeared to be quite prominent. |
| P93-1009 68 193:197 A second question is how this conception of discourse processing may be integrated with theories of discourse structure (Grosz and Sidner, 1986; Scha and Polanyi, 1988; Webber, 1991). |
| W90-0116 69 18:193 Similarly, it is unclear what work a system like that of Grosz and Sidner (1986) would do in analyzing a description. |
| E91-1015 70 187:217 Gross, B.J. and C.L. Sidner (1986) "Attention, Intentions, and the structure of discourse s . Computational Linguistics, Vol. |
| E91-1015 71 15:217 In the latter approach there is no means to describe and deal with pure discursive phenomena {meta-communication) such as oral misunderstanding, initiative keeping, initiative giving etc, Whilst in the first approaches there is no attempt to develop a full dialogue system, except in Grosz's and Sidner's {1986) model that unfortunately does not cover all oral dialogue phenomena (Bilange et al, 1990b). |
| E91-1015 72 59:217 A transaction can be viewed as a discourse segment (Grosz & Sidner~ 1986). |
| C08-1129 73 59:215 The first type is discourse markers (Moser and Moore, 1995; Schiffrin, 1987; Grosz and Sidner, 1986; Passonneau and Litman, 1997; Bangerter and Clark, 2003). |
| W00-1001 74 84:144 6 Dialogue Structure and Constraints on Multiple Exchanges 6.1 Dialogue Segment In the previous discourse model(Grosz and Sidner, 1986), a discourse segment has a beginning and an ending utterances and may have smaller discourse segments in it. |
| C90-2069 75 173:182 Second, we are extending the algorithm to make connections with work on focus of attention and discom'se structure (such as Grosz & Sidner 1986); in particular, we are investigating how resolving anaphora and tracking the current point of view are related (Stark 1987, Hewitt 1988). |
| C08-1123 76 5:180 1 Introduction A number of researchers (Hirschberg and Litman, 1993; Grosz and Sidner, 1986) speak of cue or key phrases in utterances that can serve as useful indicators of discourse structure. |
| J97-1005 77 49:736 The linguistic structure of Grosz and Sidner's (1986) discourse model consists of multiutterance segments and structural relations among them, yielding a discourse tree structure. |
| J97-1005 78 84:736 In sum, relatively few quantitative empirical studies have been made of how to annotate discourse corpora with features of discourse structure, and those recent ones that exist use various models such as the Grosz and Sidner model (1986), an informal notion of topic (Hearst 1994; Flammia and Zue 1995), transactions (Isard and Carletta 1995), Relational Discourse Analysis (Moser and Moore 1995), or control (Whittaker and Stenton 1988; Walker and Whittaker 1990). |
| J97-1005 79 48:736 2.1 Characterizing the Notion of a Segment A number of alternative proposals have been presented, which relate segments to intentions (Grosz and Sidner 1986), Rhetorical Structure Theory (RST) relations (Mann and Thompson 1988) or other semantic relations (Polanyi 1988; Hobbs 1979). |
| J97-1005 80 93:736 2.2 Correlation of Segmentation with Utterance Features The segmental structure of discourse has been claimed to constrain and be constrained by disparate phenomena, e.g., cue phrases (Hirschberg and Litman 1993; Grosz and Sidner 1986; Reichman 1985; Cohen 1984), plans and intentions (Carberry 1990; Litman and Allen 1990; Grosz and Sidner 1986), prosody (Hirschberg and Pierrehumbert 1986; Butterworth 1980), nominal reference (Webber 1991; Grosz and Sidner 1986; Linde 1979), and tense (Webber 1988; Hwang and Schubert 1992; Song and Cohen 1991). |
| J97-1005 81 89:736 We use an informal notion of communicative intention as the segmentation criterion, motivated by Grosz and Sidner (1986) and Polanyi (1988), who argue that defining a segment as having a coherent goal is more general than establishing a repertoire of specific types of segment goals. |
| J97-1005 82 59:736 Several studies have used trained coders to locally and globally structure spontaneous or read speech using the model of Grosz and Sidner (1986), including Grosz and Hirschberg 1992; Nakatani, Hirschberg, and Grosz 1995; Stifleman 1995; Hirschberg and Nakatani 1996. |
| J97-1005 83 55:736 As in Grosz and Sidner's (1986) model, Polanyi (1988) proposes that DCUs (analogous to segments) are structured as a tree, and in both models, the tree structure of discourse constrains how the discourse evolves, and how referring expressions are processed. |
| J97-1005 84 409:736 NA + + t NA + + f NA NA NA NA t NA + + f studies on data from corpora (Passonneau 1993) or published excerpts (Grosz 1977; Grosz and Sidner 1986). |
| J97-1005 85 688:736 Conclusion and Future Directions Our initial hypotheses regarding discourse segmentation were that multiutterance segment units reflect discourse coherence, and that while the semantic dimensions of this coherence may vary, it arises partly from consistency in the speaker's communicative goals (Grosz and Sidner 1986; Polanyi 1988). |
| J97-1005 86 142:736 108 Passonneau and Litman Discourse Segmentation 3.1 Methodology: Empirically Derived Segmentation The claim has been made that different people (investigators or subjects) are likely to assign similar segment boundaries or segment relations to a discourse (Grosz and Sidner 1986; Reichman 1985; Mann and Thompson 1988), but it has also been observed that discourse structure can be ambiguous (Pierrehumbert and Hirschberg 1987). |
| J97-1005 87 119:736 By statistically analyzing distributions of discourse anaphora with respect to control-based discourse segments, Walker and Whittaker (1990) showed that shifts of attentional state (Grosz and Sidner 1986) occurred when shifts in control were accepted by all dialogue participants. |
| E93-1031 88 86:291 Kamp 1981), but goes on to assume with Grosz and Sidner (1986) that candidate discourses possess hierarchical structure, with units linked by discourse relations modelled after those proposed by Hobbs (1985) (cf. |
| P98-2155 89 19:155 We propose a new theory of the relationship between accent and attention, based on an enriched taxonomy of given/new information status provided by both the LOCAL (centering) and GLOBAL (focus stack model) attentional state models in Grosz and Sidner's discourse modeling theory (1986). |
| P98-2155 90 9:155 The theory describes for the first time the interacting contributions to accent prediction made by factors related to the local and global attentional status of discourse referents in a discourse model (Grosz and Sidner, 1986). |
| C02-1035 91 21:279 In particular, MIND uses a representation called conversation segment to group together inputs that contribute to a same goal or sub-goal (Grosz and Sidner, 1986). |
| C04-1019 92 140:151 Indeed, the COLLAGEN architecture, like that of the Queens Communicator, manages discourse using a focus stack, a classical idea in the theory of discourse structure (Grosz and Sidner, 1986). |
| J98-2001 93 494:640 The presence of such a large number of discourse-new definite descriptions is also problematic for the idea that definite descriptions are interpreted with respect to the global focus (Grosz 1977; Grosz and Sidner 1986). |
| P95-1040 94 45:69 However, unlike attentional structures which are ephemeral in various time scales and empty at the end of the discourse (Grosz and Sidner, 1986), mutual beliefs persist throughout the conversation, preserving at the end the semantic and pragmatic outcome of the discourse. |
| P95-1040 95 5:69 Introduction To predict and track the center of attention in discourse, theories of centering (Grosz et al. , 1983; Brennan et al. , 1987; Grosz et al. , 1989) and immediate focus (Sidner, 1986) rely on syntactic and grammatical features of the text such as pronominalization and surface sentence position. |
| C98-1087 96 29:166 2 Theories of focus Space unfortunately prevents a full discussion of Grosz's (1977), Sidner's (1979), and G&S's (1986) theories of focus and the attentional state in this abstract. |
| C98-1087 97 26:166 Unlike Sidner's theory of focus (Sidnet; 1979), tile theory of the attentional state in (Grosz and Sidner, 1986) (henceforth: G&S) does not include explicit provision for long-distance pronominalisations, although some of the necessary tools am potentially already there, as we will see. |
| J88-3010 98 19:88 For instance, it is important to determine the cases where the goal underlying an utterance "contributes to the satisfaction of" the goal underlying another utterance--e.g. , getting the hearer to believe some proposition p contributes to the satisfaction of getting the hearer to believe some proposition q (determined as dominance relations in Grosz and Sidner (1986). |
| J88-3010 99 12:88 As soon as this kind of history of objects is included (covered in the model of Grosz and Sidner (1986) by tracking attentional state and the objects currently in focus), there are elements that are not specifically attached to the user himself. |
| J88-3010 100 14:88 Which of the actual utterances of the discourse group together into logical segments is covered by the "linguistic structure" of Grosz and Sidner (1986). |
| J88-3010 101 64:88 The examples provided in Grosz and Sidner (1986), for instance, only record those attached to segments of more than one utterance. |
| J88-3010 102 17:88 Here, I would reinterpret slightly the term as used in Grosz and Sidner (1986) (see Cohen 1986). |
| J88-3010 103 62:88 And the whole pole comes off Plan of Speaker: The top level goal is get pole off, which succeeds if the following hierarchy of subgoals succeeds: get po~ off ~_ loosen screw with wrench -~" slip in pliers identi~/scr/ew ~ identify wrench know chars, of screw know c'~hars, of wrench Intentional structure of discourse (as in Grosz and Sidner 1986): Primary Intentions: I1: intend H (get pole off); I2: intend H (loosen screw with wrench) I3: intend H (identify screw) Computational Linguistics, Volume 14, Number 3, September 1988 89 Robin Cohen On the Relationship Between User Models and Discourse Models Segmentation Structure: ( ( ( 1 2 (ds3)) 3 4 (ds2)) 5 6 (dsl)) There are three segments: ds3 with 13, ds2 with 12, and dsl with I1, where 12 DOM 13 and I1 DOM 12 (i.e. 13 contributes to the satisfaction of 12, etc). |
| J88-3010 104 6:88 I essentially include in the discourse all the components covered by the model of Grosz and Sidner (1986). |
| J88-3010 105 46:88 Schuster seems to suggest that some of the structuring provided in Grosz and Sidner (1986) is there only to highlight the entities, In my view, the actual utterances themselves are worth examining as participating in some structure. |
| W02-1702 106 8:103 This process is normally seen as a goal-directed activity in which text segments are fit into the discourse structure of the text so as to convey a coherent communicative goal (Grosz and Sidner 1986). |
| P95-1018 107 166:176 RDA is a synthesis of ideas from two theories of discourse structure (Grosz and Sidner, 1986; Mann and Thompson, 1988). |
| P95-1018 108 36:176 Previous research (Hobbs, 1985; Grosz and Sidner, 1986; Schiffrin, 1987; Mann and Thompson, 1988; Elhadad and McKeown, 1990) suggests that these factors include structural features of the discourse, intentional and informational relations in that structure, givenness of information in the discourse, and syntactic form of discourse constituents. |
| P95-1018 109 51:176 This approach synthesizes ideas which were previously thought incompatible from two theories of discourse structure, the theory proposed by Grosz and Sidner (1986) and Rhetorical Structure Theory (RST) proposed by Mann and Thompson (1988). |
| C92-2096 110 45:194 By making the intentional structure of a paragraph explicit, this work follows the discourse structure theory advanced in (Grosz & Sidner, 1986). |
| W99-0103 111 163:241 If the items have the same priority, the algorithm ranks them by the obliqueness of grammatical relation of the subcategorized functions of the main verb: that is, first the subject, object, and objects2, followed by other subcategorized fen~ons, and finally, adjuncts (Grosz and Sidner (1986), Brennan et ul. |
| W04-0214 112 129:155 There are many different schemes to choose from, for example Rhetorical Structure Theory (Mann and Thompson, 1986) or the stack model (Grosz and Sidner, 1986) and manually annotating with these schemes has variable reliability. |
| W04-0214 113 26:155 There has been plenty of theoretical work such as (Grosz and Sidner, 1986), (Moser and Moore, 1996) which shows that just as sentences can be decomposed into smaller constituents, a discourse can be decomposed into smaller units called discourse segments. |
| W07-0301 114 14:166 Conversely, dialog systems for troubleshooting in the literature have not attempted to model uncertainty directly (Grosz and Sidner, 1986; Lochbaum, 1998). |
| W97-0601 115 147:212 Thus the goal of the tagging is to show how the structure of the dialogue reflects the structure of the task (Carbelrry, 1989; Grosz and Sidner, 1986; Litman and Allen, 1990). |
| P01-1014 116 69:159 It is possible that thesis statements reflect an intentional facet (Grosz and Sidner, 1986) of language, while summary sentences reflect a semantic one (Martin, 1992). |
| W04-0712 117 133:237 By 4The reader may recognize a certain similarity of the considerations in this section with the approach of (Grosz and Sidner, 1986). |
| H92-1089 118 8:151 We present results of a study of the relationship between intonational features including pitch range, timing, and amplitude and aspects of discourse structure defined in terms of Grosz and Sidner's (1986) model of discourse. |
| W97-0621 119 11:114 (Hobbs, 1979; Reichman, 1985; Grosz and Sidner, 1986; Lochbaurn, 1991). |
| W99-0304 120 77:180 2(3 m m m \[\] m m \[\] m m m m m m \[\] m m mm m m h Data Map task group scheduling route direction telephone shopping appointment scheduling Total II \[ l umber of utterance II P 'A) P(E) Table 1: Evaluation of utterance unit tagging scheme first version second version agree 3 agree 2 disagree agree 3 60 51 1 41 38 8 0 3 35 86 24 1 26 28 6 30 31 87 29 245 119 \[ ii 218 375 agree 2 disagree 54 18 12 4 6 9 20 4 21 11 i13 46 377 0.76 0.68 0.44 0.12 0.57 0.64 3 Discourse Structure 3.1 First annotation scheme Grosz and Sidner proposed a model of discourse structure, in which discourse structure is composed of the linguistic structure, the intentional structure, and the attentional state (Grosz and Sidner, 1986). |
| J95-1003 121 378:517 The second alternative referent resolution model is that of Grosz and Sidner (1986). |
| J95-1003 122 5:517 The model is contrasted with two alternative referent resolution models, namely, a simplistic one and the more sophisticated model proposed by Grosz and Sidner (1986). |
| J95-1003 123 56:517 Subsequently, in Section 5, we present some user interactions with EDWARD and we compare the results of EDWARD's referent resolution model with two other models including that of Grosz and Sidner (1986). |
| J95-1003 124 336:517 Assessing the Quality of EDWARD's Referent Resolution Model To assess the quality of EDWARD's referent resolution model, we collected a series of referring expressions, which were processed by three different referent resolution models, namely that of EDWARD, as described above, a very simplistic model, and the sophisticated and often applied model proposed by Grosz and Sidner (1986). |
| J95-1003 125 477:517 Discourse intentions play a primary role in explaining discourse structure, defining discourse coherence, and providing a coherent conceptualization of the term "discourse" (Grosz and Sidner 1986). |
| J95-1003 126 40:517 Like XTRA, CUBRICON uses two models to interpret deictic expressions: an attentional discourse focus space representation (adapted from Grosz and Sidner 1986) and a display model. |
| J95-2003 127 31:526 Centering fits within the theory of discourse structure developed by Grosz and Sidner (1986). |
| J94-2003 128 100:759 Centering has its computational foundations in the work of Grosz and Sidner (Grosz 1977; Sidner 1979; Grosz and Sidner 1986) and was further developed by Grosz, Joshi, and Weinstein (1983, unpublished) and Joshi and Weinstein (1981). |
| J94-2003 129 101:759 Centering is intended to reflect aspects of ATYENTIONAL STATE in a tripartite view of discourse structure that also includes INTENTIONAL STRUCTURE and LINGUISTIC STRUCTURE (Grosz and Sidner 1986). |
| J96-3006 130 2:250 In this paper, we argue that the main theories representing these two approaches, RST (Mann and Thompson 1988) and G&S (Grosz and Sidner 1986), make similar claims about how speakers' intentions determine a structure of their discourse. |
| J96-3006 131 8:250 Introduction Within the computational discourse community, there is a long-standing debate between proponents of theories based on domain-independent rhetorical relations (most notably Rhetorical Structure Theory, Mann and Thompson 1988, henceforth RST; see also Hobbs 1985) and those who subscribe to theories based on intentionality (most notably that of Grosz and Sidner 1986, henceforth G&S). |
| J96-3006 132 13:250 The relations between intentions indicate whether one intention contributes to the satisfaction of another (dominance) or whether one intention must be satisfied before another (satisfaction-precedence) (Grosz and Sidner 1986). |
| J96-3006 133 19:250 Grosz and Sidner (1986) argued that intentional structure is crucial for anaphora resolution and plan recognition. |
| J01-4003 134 50:334 2.2 Centering Theory and BFP's Algorithm Centering theory is part of a larger theory of discourse structure developed by Grosz and Sidner (1986). |
| J88-2006 135 103:580 In Grosz and Sidner (1986) it is an entire focus space (FS) (Grosz 1977) that gets stacked (i.e. , the collection of entities L is attending to by virtue of the current discourse segment (DS)) but only when the 9purpose of the current DS is taken to dominate that of the one upcoming. |
| J88-2006 136 111:580 The significance of Sidner (1983) and Grosz and Sidner (1986) for the current enterprise is that: Computational Linguistics, Volume 14, Number 2, June 1988 63 Bonnie Lynn Webber Tense as Discourse Anaphor Sidner essentially shows how DF can move gradually among the discourse entities that make up a focus space, as the listener is processing its associated discourse segment; Grosz and Sidner show how DF can make a radical jump to a different (possibly newly evoked) discourse entity as the listener moves to process the next discourse segment. |
| P98-2135 137 10:67 Broadcast News Analysis Human communication is characterized by distinct discourse structure (Grosz and Sidner 1986) which is used for a variety of purposes including managing interaction between participants, mitigating limited attention, and signaling topic shifts. |
| E06-3001 138 112:200 5 Preliminary Model Overviews The models evaluated in this paper are based on Centering Theory (Grosz et al. , 1995; Grosz & Sidner, 1986) and the algorithms devised by Brennan and colleagues (1987) and adapted by Tetreault (2001). |
| E87-1042 139 1:184 TEMPORAL REASONING IN NATURAL LANGUAGE UNDERSTANDING: THE TEMPORAL STRUCTURE OF THE NARRATIVE Alexander Nakhimovsky Department of Computer Science Colgate University Hamilton, NY 13346 USA CSNet: sasha@colgate Abstract This paper proposes a new framework for discourse analysis, in the spirit of Grosz and Sidner (1986), Webber (1987a,b) but differentiated with respect to the type or genre of discourse. |
| E87-1042 140 17:184 Grosz and Sidner, 1986:184). |
| E87-1042 141 9:184 It also builds on the ideas of Grosz and Sidner (1986), but reformulates them specifically for the task of narrative understanding. |
| J95-3001 142 22:965 These are called "segments" by Grosz and Sidner (1986) and constitute the linguistic structure defined in their paper. |
| J95-3001 143 775:965 Grosz and Sidner (1986) use the notation DP and DSP to stand for "discourse purpose" and "discourse segment purpose". |
| J95-3001 144 299:965 Expectation of user responses provides a model of the attentional state described by Grosz and Sidner (1986). |
| J95-3001 145 18:965 This is the intentional structure of Grosz and Sidner (1986), the goaloriented mechanism that gives direction to the interaction. |
| J95-3001 146 57:965 This is the attentional structure described by Grosz and Sidner (1986), and its most important function in our system is to predict the meaning structures the user is likely to communicate in an input. |
| J95-3001 147 762:965 Theoretical Issues from the Literature Grosz and Sidner (1986) have given a high-level theory of dialog. |
| W99-0106 148 16:182 The fact that current anaphora resolution systems rely exclusively on the linear nature of texts in Order to determine the LPA of an anaphor seems odd, given that several studies have claimed that there is a strong relation between discourse structure and reference (Sidner, 1981; Gmsz and Sidner, 1986; Grosz et aL, 1995; Fox, 1987; Vonk et al. , 1992; Azzam et al. , 1998; Hitzeman and P.oesio, 1998). |
| W94-0324 149 30:448 Its domain is the maintenance of electrical appliances, and the emphasis in this approach lies on (nested) communicative goals, and concepts such as intentional, attentional and linguistic structures (Grosz and Sidner, 1986). |
| W94-0324 150 64:448 In the area of conversational analysis and discourse theory, on the other hand, we find various discourse and dialogue models which address local dialogue structures (e.g. , Fawcett et al. , 1988; Grosz and Sidner, 1986, 1990; Reichman, 1985). |
| W00-1007 151 7:279 Centering fits into Grosz and Sidner's model of discourse structure (Grosz and Sidner, 1986). |
| J93-3003 152 14:479 The structural information conveyed by these phrases is crucial to many tasks, such as anaphora resolution (Grosz 1977; Grosz and Sidner 1986; Reichman 1985), the inference of speaker intention and the recognition of speaker plans (Grosz and Sidner 1986; Sidner 1985; Litman and Allen 1987), and the generation of explanations and other text (Zuckerman and Pearl 1986). |
| J93-3003 153 305:479 This talk yielded 953 tokens, based upon a set of possible cue phrases derived from Cohen (1984), Grosz and Sidner (1986), Litman and Hirschberg (1990), Reichman (1985), Schiffrin (1987), Warner (1985), and Zuckerman and Pearl (1986). |
| J93-3003 154 60:479 For example, it has been shown that cue phrases can assist in the resolution of anaphora, by indicating the presence of a structural boundary or a relationship between parts of a discourse (Grosz 1977; Grosz and Sidner 1986; Reichman 1985). |
| J93-3003 155 76:479 Grosz and Sidner (1986), in their tripartite model of discourse structure, classify cue phrases based on the changes they signal to the attentional and intentional states. |
| J04-2001 156 8:507 Introduction Centering has been proposed as a model of the local attentional states of speakers and hearers involved in the mutual construction of conversation (Brennan, Friedman, and Pollard 1987; Grosz and Sidner 1986, 1998; Walker 1998). |
| P06-2097 157 120:192 3.1.2 Cue phrases As Grosz and Sidner (Grosz and Sidner, 1986) pointed out, cue phrases such as now and well serve to indicate a topic change. |
| C98-2183 158 42:146 Researchers in discourse, such as Grosz and Sidner (1986), Lambert (1993), Hirschberg and Litman (1993), Chen (1995), Andernach (1996), Samuel (1996), and Chu-Carroll (1998) have suggested several features that might be relevant for the task of computing dialogue acts. |
| J88-3008 159 49:152 It is important to note that the representations of entities, as they appear in the discourse have a structure as proposed by Grosz and Sidner (1986). |
| J87-1002 160 318:436 (See also Grosz and Sidner 1986). |
| J87-1002 161 388:436 Because of similarities in the representations and techniques for controlling search for interpretations, it is worth investigating as future work the precise relationship among coherence, reference resolution and focus determination for dialogues (some of this is being done (Grosz and Sidner 1986)). |
| J87-1002 162 434:436 This research is of significance to the current work of Grosz and Sidner (1986). |
| J87-1002 163 142:436 It is also distinct from the investigations of Reichman (1981) and (recently) Grosz and Sidner (1986). |
| J87-1002 164 286:436 The difficulties in plan inference for discourse are discussed in more detail in Grosz and Sidner (1986), and are in fact a topic of our current concern (see discussion of future work in Section 6). |
| C88-2114 165 56:166 Focus space k.~ Speaker Display OAct Act type Act structure \ Figure 1" Structural components of the model 2.3 Cotmmunicative Situation Structures The Conmtunicative Situation Structure (CSS) is equivalent in level of analysis to the discourse segment of the Grosz and Sidner (1986) model. |
| W93-0225 166 13:118 In a tirst step towards the synthesis we wouhl like to see, we will discuss the l~erspective which the G&S (Grosz and Sidner 1986) and RST (=RhetoricaJ Structure Theory, Ma.nn and Thompson 1988) theories take on links of meaning a.nd function. |
| W03-2101 167 70:182 Grosz and Sid- ner(Grosz and Sidner, 1986) claim that a robust model of discourse understanding must use mul- tiple knowledge sources in order to recognize the complex relationships that utterances have to one another. |
| W03-2101 168 63:182 Each discourse segment has a discourse seg- ment purpose that contributes to the discourse purpose or intention underlying the overall dis- course(Grosz and Sidner, 1986). |
| C90-3018 169 141:306 Some researchers (Grosz & Sidner, 1986, Hirschberg & Litman, 1987) seem to argue that it does: the cue and non-cue usages are actually two distinct words. |
| C90-3018 170 36:306 Work on the structure of discourse (Cohen, 1984, Reichman, 1985, Grosz & Sidner, 1986) has identified the role of connectives in marking structural shifts. |
| W00-1013 171 172:218 4See (Grosz and Sidner, 1986) for a discussion of the importance of task plans in more explanatory dialogue. |
| P95-1005 172 43:241 We challenge an assumption underlying the best known theories of discourse structure (Grosz and Sidner 1986; Scha and Polanyi 1988; Polanyi 1988; Mann and Thompson 1986), namely that discourse has a recursive, tree-like structure. |
| P95-1005 173 12:241 From a theoretical standpoint, we will demonstrate that theories which postulate a strict tree structure of discourse (henceforth, Tree Structure Theory, or TST) on either the intentional level or the attentional level (Grosz and Sidner 1986) are not totally adequate for covering spontaneous dialogues, particularly negotiation dialogues which are composed of multiple threads. |
| P95-1005 174 50:241 We develop our theory of discourse structure in the spirit of (Grosz and Sidner 1986) which has played an influential role in the analysis of discourse entity saliency and in the development of dialogue processing systems. |
| J92-4007 175 6:133 The basic problem is that an RST representation of a discourse does not fully specify the intentional structure (Grosz and Sidner 1986) of that discourse. |
| J92-4007 176 76:133 4 In Grosz and Sidner (1986), dominates and satisfaction-precedence are the intentional relations, while supports and generates are the informational relations. |
| J92-4007 177 10:133 In fact, as has been noted in other work on discourse structure (Grosz and Sidner 1986), discourse elements are related simultaneously on multiple levels. |
| P98-2179 178 53:120 The rules of inference are clear candidates for operationalisation: moves such as Modus Ponens are clearly vital components of any argument though, as noted in Grosz and Sidner (1986), p201, it is inappropriate to view the implication step as one of conventional material implication. |
| P98-2179 179 51:120 The roles of these goals and their interrelationships are explored in relation to the informationintention-attention model of Grosz and Sidner (1986) in more detail in Reed and Long (1997a). |
| P07-1101 180 5:183 1 Introduction CUE PHRASES (also known as DISCOURSE MARKERS) are linguistic expressions that can be used to convey explicit information about the structure of a discourse or to convey a semantic contribution (Grosz and Sidner, 1986; Reichman, 1985; Cohen, 1984). |
| C94-2187 181 33:138 Fnrthermore, we do not intend the disD Figure 1: Discourse Structure course structure to be anything close to the ones that rhetorical theories of discourse (tIovy, 1990; Mann and Tholnpson, 1987; Itobbs, 1979) claim it to be, or inteulional structure (Grosz and Sidner, 1986) ; indeed we do not assmne any functional relation, i.e. causation, elaboration, extension, etc. , among the segments that constitute a discourse structure. |
| W99-0101 182 52:215 As in Grosz & Sidner (1986), discourse is organized by the interlocutors' goals and intentions and the plans, or strategies, which conversational participants develop to achieve them. |
| W00-1430 183 65:288 2.2 Attention focus and Information Structure Theory . Other researchers have investigated attention focus in larger spans of discourse .(McCoy and Cheng, 1991; Grosz and Sidner, 1986) and in dialogue (Jokinen et al. , 1998). |
| W97-1411 184 74:92 Coherence The coherence of the proceeding dialogue should not be damaged by an object becoming the referent of the expression (Grosz and Sidner, 1986). |
| W06-1309 185 9:198 Examples of such models and their implementation are the informationstate-update approach (an implemented system is described in (Larsson, 2002)), or more linguisticallyorientedapproachesliketheadjacency-pair models or intentional models such as GROSZ and SIDNERs (see (Grosz and Sidner, 1986)). |
| C96-1052 186 99:171 ((:2) Pronominalize objects in the focus of attention (Grosz and Sidner 1986). |
| W04-2318 187 8:96 These structures may be viewed as corresponding tointentional structure of discourse segment purposes in the view of (Grosz and Sidner, 1986), to plan and subplan structure directly in the view of (Allen and Litman, 1990), to nuclei and satellite rhetorical relations in the Rhetorical Structure Theory of (Mann and Thompson, 1987), or to information structures as in (Traum and Hinkelman, 1992). |
| J88-3013 188 79:85 A shifting focus of attention like that represented by the point of interaction between participants and discourse in Grosz and Sidner's (1986) account is naturally presupposed here. |
| W07-1408 189 139:145 Geneva, (206) 3-10 Grosz B. and C. Sidner 1986. |
| W07-1408 190 90:145 3.1 Focusing Revisited Our version of the focusing algorithm folows Sidner?s proposal (Sidner C. , 1983; Grosz B. , Sidner C. , 1986), to use a Focus Stack, a certain Focus Algorithm with Focus movements and data structures to allow for processing simple inferential relations between different linguistic descriptions co-specifying or coreferring to a given entity. |
| W00-1420 191 133:201 The context contains a stack for objects in focus, handled as described in (Grosz and Sidner, 1986). |
| W93-0229 192 17:84 Because a conversation is a temporal sequence of connected illocutionary acts 110 (Moulin, Rousseau and Vanderveken 1991) where each speech act plays a precise role in the context of other speech acts, some researchers have studied the structure of a conversation and they all agreed that there are several interrelated components in it and many subconversations of different types (Grosz and Sidner 1986, Litman and Allen 1987). |
| E06-3002 193 40:193 (Grosz and Sidner, 1986) incorporates two more important notions into its model the idea of intention and focus. |
| J97-1006 194 240:606 Finally, integration of theorems, the utterances relevant to these theorems, and the expectations for responses that supply missing axioms yields a constructive method for creating and using a discourse model first proposed by Grosz and Sidner (1986), but for which they did not offer a method of dynamic construction during the course of a dialogue. |
| J00-4003 195 753:766 Our analysis of these data, as well as of other corpora (Hitzeman and Poesio 1998), suggests that a local focusing mechanism as proposed in Grosz (1977), Sidner (1979), Grosz, Joshi, and Weinstein (1983, 1995), and Grosz and Sidner (1986) would improve the results obtained by our system. |
| J00-4003 196 155:766 549 Computational Linguistics Volume 26, Number 4 In general, it is not sufficient to look at the most recent antecedents only: this is because segments are organized hierarchically, and the antecedents introduced in a segment at a lower level are typically not accessible from a segment at a higher level (Fox 1987; Grosz 1977; Grosz and Sidner 1986; Reichman 1985), whereas the antecedents introduced in a prior segment at the same level may be. |
| W96-0410 197 104:250 Second, entities differ in SALIENCE (Grosz and Sidner, 1986; Grosz et al. , 1995). |
| W98-0301 198 5:169 These segments were defined intentionally in terms of Grosz and Sidner's theory (1986) or in terms of an intuitive notion of "topic". |
| H05-1090 199 118:217 Pronouns are known to signal that the same focus continues (Grosz and Sidner, 1986). |
| J91-1002 200 94:606 We will describe the application of lexical cohesion to the determination of the discourse structure that was proposed by Grosz and Sidner (1986). |
| J91-1002 201 374:606 The text structure theory chosen for this analysis was that of Grosz and Sidner (1986). |
| J91-1002 202 531:606 The lexical chains computed by the algorithm given in Section 3.2.3 correspond closely to the intentional structure produced from the structural analysis method of Grosz and Sidner (1986). |
| C00-1031 203 20:182 The fact that current anaphora resolution systems rely exclusively on the linear nature of texts in order to determine the LPA of an anaphor seems odd, given flint several studies have claimed that there is a strong relation between discourse structure and reference (Sidner, 1981 ; Grosz and Sidner, 1986; Grosz et al. , 1995; Fox, 1987; Vonk ct al. , 1992; Azzam el al. , 1998; Hitzcman and Pocsio, 1998). |
| C92-2114 204 145:236 4.1 Input We limit our scope to the linguistic part of generation; therefore, we assume that onr input is the ontput of a text planner, which has already grouped actions into discourse structures as proposed by Grosz and Sidner (1986) and (Dale 1988), The input is thus a sequence of actions and states in which participants (ingredients, instruments and agent) are represented by indices. |
| W05-1606 205 22:212 A context set is defined as the set of the entities the addressee is currently assumed to be attending to this is similar to the set of entities in the focus spaces of the discourse focus stack in Grosz' and Sidner's [1986] theory of discourse structure. |
| W01-1603 206 60:200 ---------------------------------------[TBI:topic name:segment relation] Figure 5: An example dialogue with the dialogue segment tags 2.3 Dialogue segment DialoguesegmentofJDTAGindicatesboundaryof discourse segment introduced in (Grosz and Sidner, 1986). |
| P92-1025 207 129:198 Since linguistic knowledge is present, less evidence is needed from world knowledge to recognize the discourse actions being performed (Grosz and Sidner, 1986). |
| P92-1025 208 115:198 5 Combining Knowledge Sources Grosz and Sidner (1986) contend that modeling discourse requires integrating different kinds of knowledge in a unified framework in order to constrain the possible role that an utterance might be serving. |
| W06-3001 209 16:237 (1990) this is given by the discourse goals, rather than the overall goals of the user, as is the case in task-oriented dialogues, (Grosz and Sidner, 1986). |
| W06-3001 210 207:237 We can speak of thematic nesting of segments, which seems to be analogous to the intentional structure in taskoriented dialogues as in (Grosz and Sidner, 1986), also allowing for reference with implicit devices to entities in the superordinate segments after the subordinated ones have been closed. |
| P97-1027 211 18:153 A context set is defined as the set of entities the addressee is currently assumed to be attending to this is similar to the set of entities in the focus spaces of the discourse focus stack in Grosz and Sidner's theory of discourse structure (Grosz, Sidner, 1986). |
| W99-0208 212 34:162 The aim of this attribute is to use the often mentioned relationship between topicality and coreference (see Grosz and Sidner 1986) for operational purposes. |
| P97-1035 213 189:328 Then using the performance equation above, predicted performance for RA is: Performance(Ra) = .40 .71 -.78 .72 = --0.28 For Agent B, using the appropriate subpart of Table 4 to calculate ~, assuming that the average number of depart-city repair utterances is 1.38, and using similar 12This assumption has a sound basis in theories of dialogue structure (Carberry, 1989; Grosz and Sidner, 1986; Litman and Allen, 1990), but should be tested empirically. |
| P97-1035 214 130:328 Since the structure of a dialogue reflects the structure of the task (Carberry, 1989; Grosz and Sidner, 1986; Litman and Allen, 1990), the tagging of a dialogue by the AVM attributes can be used to generate a hierarchical discourse structure such as that shown in Figure 4 for Dialogue 1 (Figure 2). |
| J88-3012 215 78:85 On the other hand, the user's utterances can also be analyzed from another viewpoint, namely incorporating them into a coherent discourse model as described by, e.g., Grosz and Sidner (1986). |
| J88-3012 216 35:85 As opposed to Schuster, who defines a discourse model as "containing representations of entities, along with their properties and relations they participate in", which corresponds exactly to our dialog memory, I use discourse model according to the framework of Grosz and Sidner (1986), where a discourse model is the syntactic structure of a dialog. |
| C88-1044 217 25:284 It is this view which most closely reflects the assumptions underlying computationaUy explicit models of focus-constrained discourse processing (e.g. , Linde 1979; Reichman 1985; Grosz and Sidner 1986). |
| C88-1044 218 257:284 While such a model could be incorporated into existing discourse structure frameworks (e.g. Grosz and Sidner 1986), no specific proposals to account for shared familiarity have yet been advanced (but see Sparck Jones 1986). |
| C88-1044 219 264:284 At the global level, Sidner and Grosz (1986) describe a model of discourse structure which indicates currently activated beliefs and intentions at any given point in a discourse. |
| C88-1044 220 10:284 Grosz and Sidner 1986). |
| P98-1065 221 9:137 Knowledge-based systems as Grosz and Sidner's (1986) require an extensive manual knowledge engineering effort to create the knowledge base (semantic network and/or frames) and this is only possible in very limited and well-known domains. |
| P00-1053 222 5:193 We compare VT to stack-based models based on Grosz and Sidner's (1986) focus spaces, and show how VT addresses the problem of "left satellites", i.e., subordinate discourse segments that appear prior to their nuclei (dominating segments) in the linear text. |
| P00-1053 223 64:193 Here, we compare VT to stack-based models of discourse structure based on Grosz and Sidner's (1986) (G&S) focus spaces (e.g. , Hahn and Strbe, 1997; Azzam, et al. , 1998). |
| C98-2150 224 20:152 We propose a new theory of the relationship between accent and attention, based on an enriched taxonomy of given/new information status provided by both the LOCAL (centering) and GLOBAL (foCUS stack model) attentional state models in Grosz and Sidner's discourse modeling theory (1986). |
| C98-2150 225 10:152 The theory describes for the first time the interacting contributions to accent prediction made by factors related to the local and global attentional status of discourse referents in a discourse model (Grosz and Sidner, 1986). |
| W01-0814 226 168:201 5.4 Anaphora and ellipsis Several works have explored the relation between rhetorical structure and reference in English (Fox, 1987; Cristea et al. , 2000; Grosz and Sidner, 1986; Grosz et al. , 1995). |
| W04-0203 227 33:234 These relations have syntactic aspects, such that single utterances can be grouped together and combined into segments recursively and are often modeled as a hierarchical tree structure (Grosz and Sidner, 1986; Webber et al. , 1999). |
| W04-0203 228 37:234 2.1 Syntax of discourse relations One substructure of a coherent discourse structure is its attentional structure, which can be modeled as a stack of focus spaces (Grosz and Sidner, 1986). |
| C00-2130 229 43:110 Segmentalion In l i IE-spans limited MI",NTS t1131 lllay general, discourse entities have to pra?matical ly delermined,Slit; be nested (see, e.g., (Rcichman, 1985; Grosz and Sidner, 1986; Fox, 1987)). |
| C04-1075 230 21:174 While a number of approaches use a similar set of factors, the computational strategies (the way antecedents are determined, i.e. the algorithm and formula for assigning antecedents) may differ, i.e. from simple co-occurrence rules (Dagan and Itai 1990) to decision trees (Soon, Ng and Lim 2001; Ng and Cardie 2002) to pattern induced rules (Ng and Cardie 2002) to centering algorithms (Grosz and Sidner 1986; Brennan, Friedman and Pollard 1987; Strube 1998; Tetreault 2001). |
| J02-3003 231 54:880 The centering model (Grosz and Sidner 1986; Grosz, Joshi, and Weinstein 1983) makes the following assumptions: 1. |
| J02-3003 232 31:880 3 In such discourses it seems that a structural account is at play (in the sense of Grosz and Sidner [1986]). |
| J02-3003 233 256:880 The Proposal: Aposynthesis 3.1 Outline of the Discourse Model We assume that the discourse is organized hierarchically in linear and embedded segments as specified in Grosz and Sidner (1986). |
| P97-1011 234 7:222 They play a crucial role in many discourse processing tasks, including plan recognition (Litman and Allen, 1987), text comprehension (Cohen, 1984; Hobbs, 1985; Mann and Thompson, 1986; Reichman-Adar, 1984), and anaphora resolution (Grosz and Sidner, 1986). |
| P97-1011 235 13:222 Previous research (Hobbs, 1985; Grosz and Sidner, 1986; Schiffrin, 1987; Mann and Thompson, 1988; Elhadad and McKeown, 1990), which has been largely descriptive, suggests factors such as structural features of the discourse (e.g. , level of embedding and segment complexity), intentional and informational relations in that structure, ordering of relata, and syntactic form of discourse constituents. |
| P97-1011 236 38:222 It synthesizes ideas from (Grosz and Sidner, 1986) and from RST (Mann and Thompson, 1988). |
| W04-2504 237 41:230 Therefore, it is important to capture the intention from the user (Grosz and Sidner 1986). |
| W04-2504 238 84:230 Intentional transitions are closely related to Grosz and Sidners dominance and satisfaction precedence relations, which are more relevant to plan-based discourse (Grosz and Sidner, 1986). |
| A00-1005 239 43:203 Other related work on dialogue include (Carberry, 1990; Grosz and Sidner, 1986; Reichman, 1981). |
| N07-1003 240 80:260 Grosz and Sidner, 1986). |
| N07-1003 241 101:260 No claim is made that the game and card blocks are discourse segments according to Grosz and Sidners definition (1986). |
| H05-1031 242 98:186 Intuitively, pronominalization indicates that an entity was particularly salient at a speci c point of the discourse, as has been widely discussed in attentional status and centering literature (Grosz and Sidner, 1986; Gordon et al. , 1993). |
| J98-4001 243 786:1005 Intentions such as these, as well as segment beginnings and endings, might be recognized on the basis of linguistic markers, utterance-level intentions, or knowledge about actions and objects in the domain of discourse (Grosz and Sidner 1986). |
| J98-4001 244 776:1005 In their paper on discourse structure, Grosz and Sidner give several examples of the types of intentions that could serve as DSPs (Grosz and Sidner 1986, 179): 1. |
| J98-4001 245 799:1005 These mental attitudes may be ascribed on the basis of those of the OCP's beliefs that are in accord with the mental attitudes comprising the SharedPlan (Pollack 1986a; Grosz and Sidner 1990). |
| J98-4001 246 18:1005 A discourse is composed of discourse segments much as a sentence is composed of constituent phrases (Grosz and Sidner 1986). |
| J98-4001 247 820:1005 7.3 The Contextual Role of Intentional Structure An utterance of a discourse can either begin a new segment of the discourse, complete the current segment, or contribute to it (Grosz and Sidner 1986). |
| J98-4001 248 3:1005 The intentional structure of the discourse, comprised of discourse segment purposes and their interrelationships, plays a central role in this process (Grosz and Sidner 1986). |
| J98-4001 249 771:1005 We now show that this model satisfies the requirements set out by Grosz and Sidner's (1986) theory of discourse structure. |
| J98-4001 250 816:1005 The operations on the focus space stack depend upon subsidiary rela561 Computational Linguistics Volume 24, Number 4 tionships between SharedPlans in the same way that Grosz and Sidner (1986) describe the operations as depending upon DSP relationships. |
| J98-4001 251 8:1005 Their intentions guide their behavior and their conversational partners' recognition of those intentions aids in the latter's understanding of their utterances (Grice 1969; Sidner 1985; Grosz and Sidner 1986). |
| J98-4001 252 831:1005 However, as Grosz and Sidner (1986) have argued, the OCP must be able to recognize initially at least a generalization of the DSP so that the proper moves of attentional state can be made. |
| J98-4001 253 487:1005 Grosz and Sidner (1986) also describe a contributes relation between DSPs that is the inverse of the dominates relation. |
| J98-4001 254 403:1005 For each utterance of a discourse, an agent must determine whether the utterance begins a new segment of the discourse, completes the current segment, or contributes to it (Grosz and Sidner 1986). |
| J98-4001 255 801:1005 Once an OCP recognizes the initiation of a new discourse segment, it must determine the relationship of that segment's DSP to the other DSPs underlying the discourse (Grosz and Sidner 1986). |
| J98-4001 256 992:1005 For example, consider DSPs of the form "Intend that some agent intend to perform some physical task," as proposed by Grosz and Sidner (1986, 179). |
| J98-4001 257 320:1005 Grosz and Sidner's Theory of Discourse Structure According to Grosz and Sidner's (1986) theory, discourse structure is comprised of three interrelated components: a linguistic structure, an intentional structure, and an attentional state. |
| J98-4001 258 93:1005 These purposes and their interrelationships form the intentional structure of the discourse (Grosz and Sidner 1986). |
| J98-4001 259 342:1005 Following Grosz and Sidner (1986), we will refer to that agent as the ICP for initiating conversational participant; the other participant is the OCP. |
| J00-3003 260 573:607 For example, a context-free discourse grammar could potentially account for the nested structures proposed in Grosz and Sidner (1986). |
| J94-2004 261 526:704 Examples are adverbs such as 'just', 'merely', and 'only' (when used as attitude diminishers (Quirk et al. 1985)), as in "He just sat and drank" (it was expected that he would do something "more" than sit and drink) 7 Adverbials that are conjuncts, which connect units of discourse (Quirk et al. 1985) (i.e. , cue phrases; Reichman 1985, Grosz and Sidner 1986, Cohen 1987). |
| W00-0301 262 5:162 To determine the principles governing human collaboration, we have relied on research in computational linguistics on collaborative discourse, specifically within the SharedPlan framework of Grosz and Sidner (1986, 1990) (Grosz and Kraus, 1996, Lochbaum, 1998). |
| W04-2906 263 12:111 This structure, in turn, identi es domains for interpretation; many systems for anaphora resolution rely on some notion of locality (Grosz and Sidner, 1986). |
| W97-1201 264 190:202 Pitch accent placement on pronouns as well as on explicit forms in the subject position motivate theory that describes new and givenness in terms of a hierarchical discourse structure (Grosz and Sidner 1986). |
| W90-0118 265 46:149 Grosz & Sidner (1986) made similar criticisms from the standpoint of characterizing discourse coherence. |
| W08-1103 266 88:197 Therefore, it is appropriate to close the initial summary with propositions from the computational class so that the whole graphic is in the users focus of attention (Grosz and Sidner, 1986). |
| W03-2114 267 90:168 4 Top-Level Context Management The approach to dialogue modeling we have imple- mented is based on the theory of dialogue games (Carlson, 1983; Power, 1979), and, for task-oriented dialogues, discourse segments (Grosz and Sidner, 1986). |
| C00-1083 268 64:197 In some studies of dialogue management (Rich and Sidner, 1998; Stent et M. , 1999), the state of the dialogue is represented using Grosz and Sidner's framework (Grosz and Sidner, 1986). |
| W98-0317 269 118:217 3Clark (1997) presents a term "discourse topic" as concept equivalent to focus space in (Grosz and Sidner, 1986), and call their transition "discourse transition". |
| W98-0317 270 18:217 First, discourse structure is indispensable for selecting cue phrase as claimed in previous studies (Grosz and Sidner, 1986; Cohen, 1984; Eugenio et al. , 1997). |
| W98-0317 271 68:217 As the result of classifying these 31 cue phrases based on the classification of Japanese connectives (Ichikawa, 1978; Moriyama, 1997) and cue phrase classification in Enghsh (Grosz and Sidner, 1986; Cohen, 1984; Knott and Dale, 1994; Moser and Moore, 1995b), 20 cue phrases, which occurred total of 848 times, were classified into three classes: changeover, such as soredeha, deha ("now", "now then" in English), conjunctive, such as sore.de, de ("and", "and then"), and ordinal, such as mazu, tsugini ("first", "next"). |
| W98-0317 272 78:217 We define discourse segment (or simply segment) as chunks of utterances that have a coherent goal (Grosz and Sidner, 1986; Nakatani et al. , 1995; Passonneau and Litman, 1997). |
| W98-0317 273 11:217 In previous studies that have investigated the relationship between cue phrases and the types of structural change (e.g. pop, push), the taxonomies of cue phrases have been presented (Grosz and Sidner, 1986; Cohen, 1984; Schiffrin, 1987). |
| W98-0317 274 6:217 They signal topic shifts and changes in attentional state (Grosz and Sidner, 1986) as well as expressing the relation between the individual units of discourse (Moore, 1995; RSsner and Stede, 1992). |
| J99-1001 275 161:1216 The Process Model Grosz and Sidner (1986) claim that a robust model of understanding must use multiple knowledge sources in order to recognize the complex relationships that utterances have to one another. |
| J99-1001 276 93:1216 A number of researchers (Reichman 1978, 1985; Grosz and Sidner 1986; Polanyi 1986; Cohen 1987; Hirschberg and Litman 1987; Litman and Allen 1987; Schiffrin 1987; Hinkelman 1989; Litman and Hirschberg 1990; Knott and Dale 1994; Knott and Mellish 1996; Marcu 1997) have investigated the use in discourse of special words and phrases such as but, anyway, and by the way. |
| J99-1001 277 376:1216 Grosz and Sidner (1986) claim that when evidence is available from one source, less evidence should be required from others. |
| J99-1001 278 807:1216 Other Related Work 7.1 Grosz and Sidner's Theory of Discourse Processing Grosz and Sidner (1986) postulated a theory of discourse structure that included linguistic, intentional, and attentional components, and they argued that the dominance and satisfaction-precedes relationships between discourse segments must be identified in order to determine discourse structure. |
| J99-1001 279 147:1216 This claim is supported by a combination of 1) the stack paradigm (Polanyi 1986; Reichman 1978; Grosz and Sidner 1986; Litman and Allen 1987), which treats topic structure as following a stack-like discipline; 2) focusing heuristics (McKeown 1983) that suggest that if a speaker has more to say about a topic, then he should do so before moving back to a topic deeper on the stack; and 3) the notion of implicit acceptance (discussed in Section 4.6) that argues that passing up the opportunity to reject an assertion in a collaborative dialogue communicates acceptance of it. |
| C98-2130 280 10:64 Broadcast News Analysis Human communication is characterized by distinct discourse structure (Grosz and Sidner 1986) which is used lbr a variety of purposes including managing interaction between participants, mitigating limited attention, and signaling topic shifts. |
| A92-1010 281 122:300 Even though there are some critics questioning the use of rhetorical relations in discourse structure theory (Grosz and Sidner, 1986) we use 75 (rl /rst-nonvolitional-result :domain (el/ existence :domain (cl / concept :number mass :process (r2/show :saying cl :speechact denial :tense present))) :range (a/ascription :domain (c2 / capacity :owned-by (p/pres-form)) :range (ex / exceeded) :tense present))) Figure 5 : SPL-Plan for "There are concepts that are not shown, because the presentation-form's capacity is exceeded". |
| P98-2163 282 162:174 To deal with this problem, we must incorporate the notion of intentional structure and focus space structure (Grosz and Sidner, 1986). |
| P04-1049 283 67:207 3.1 Representing coherence structures 3.1.1 Discourse segments Discourse segments can be defined as nonoverlapping spans of prosodic units (Hirschberg & Nakatani (1996)), intentional units (Grosz & Sidner (1986)), phrasal units (Lascarides & Asher (1993)), or sentences (Hobbs (1985)). |
| J97-1003 284 147:581 Foremost among these are the attentional/intentional structure of Grosz and Sidner (1986) and the Rhetorical Structure Theory of Mann and Thompson (1987). |
| J97-1003 285 256:581 The chains are used to structure texts according to the attentional/intentional theory of discourse structure (Grosz and Sidner 1986) discussed above. |
| P95-1015 286 36:284 Morris and Hirst (1991) structured a set of magazine texts using the theory of (Grosz and Sidner, 1986), developed a thesaurus-based lexical cohesion algorithm to segment text, then qualitatively compared their segmentations with the results. |
| P95-1015 287 22:284 The linguistic structure of Grosz and Sidner's (1986) tri-partite discourse model consists of multi-utterance segments whose hierarchical relations are isomorphic with intentional structure. |
| P95-1015 288 5:284 (Grosz and Hirschberg, 1992; Grosz and Sidner, 1986; Hirschberg and Grosz, 1992; Hirschberg and Litman, 1993; Hirschberg and Pierrehumbert, 1986; Hobbs, 1979; Lascarides and Oberlander, 1992; Linde, 1979; Mann and Thompson, 1988; Polanyi, 1988; Reichman, 1985; Webber, 1991)). |
| P98-1044 289 13:171 Our approach is closer to that of Passonneau (1995) and Hahn and Strtibe (1997), who both use a stack-based model of discourse structure based on Grosz and Sidner's (1986) focus spaces. |
| P98-1044 290 112:171 The definition of veins formalizes these relationship, s. Given the mapping of Grosz and Sidners (1986) stackbased model of discourse structure to RST structure trees outlined by Moser and Moore (1996), the domains of referentiality defined for left-polarized trees using VT are consistent with those defined using the stack-based model (e.g. Passonneau (1995), Hahn and Strtibe (1997)). |
| P98-1044 291 117:171 7 We use Grosz and Sidner's (1986) terminology here, but note the equivalence of dominance in G&S and nucleus/satellite relations in RST pointed out by Moser and Moore (1996). |
| C96-1001 292 1:26 Discovering the Sounds of Discourse Structure* Extended Abstract Barbara J. Grosz Division of Engineering and Applied Sciences Harvard University 33 Oxford Street Cambridge, MA 02138 USA grosz(~eecs.harvard.edu It is widely accepted that discourses are composed of segments and that the recognition of segment boundaries is essential to a determination of discourse meaning (Grosz and Sidner, 1986). |
| E89-1022 293 94:175 But there is also a different perspective whose key notion is the well-established concept of focus (see e.g. in Computational Linguistics Grosz & Sidner 1986) 3. |
| W93-0222 294 13:45 One kind of evidence for constituent structure above the clause level is tile pattern of pronominalization (e.g. Grosz & Sidner's (1986) attentional structure). |
| P95-1042 295 20:85 A closely related (though not identical) problem is found in recognising boundaries in discourse, and there seems to be little agreement in the literature as to the properties and functions they possess (Morris and Hirst, 1991), (Grosz and Sidner, 1986). |
| W00-1014 296 76:253 The Dialogue history records the focus of attention (Grosz and Sidner, 1986) and contains information about objects, properties, and relations as well as other dialogue information such as speech act information and system task information. |
| W06-2302 297 111:185 1 GETARUNS AR algorithm 3.2 Focussing Revisited Our version of the focussing algorithm follows Sidners proposal (Sidner C. , 1983; Grosz B. , Sidner C. , 1986), to use a Focus Stack, a certain Focus Algorithm with Focus movements and data structures to allow for processing simple inferential relations between different linguistic descriptions co-specifying or coreferring to a given entity. |
| W93-0230 298 61:69 A good example is the work of Grosz & Sidner (1986), who present their account as antagonistic to the coherence relation approach as advocated in tiffs paper. |
| J94-4002 299 412:488 Sidner (1981, 1983), Grosz, Joshi, and Weinstein (1983, 1986), Grosz and Sidner (1986), 21 The difficulty that RAP encounters with such cases was discussed in Section 4.1. |
| J94-4002 300 18:488 It does not employ semantic conditions (beyond those implicit in grammatical number and gender agreement) or real-world knowledge in evaluating candidate antecedents; nor does it model intentional or global discourse structure (as in Grosz and Sidner 1986). |
| N04-4039 301 119:123 Pushing and popping of a discourse segment (Grosz & Sidner, 1986) may also affect gesture occurrence. |
| W93-0239 302 22:67 Notice that 'But' in (2.2) is being used to connect clauses, a.\]M not in addition to mark the beginning of a new discourse segment (as the term discourse,~:gmcnt is used in Grosz ~ Sidner 1986). |
| W04-1002 303 46:166 On the other hand, when an article is comprised of text and graphics, the graphic generally expands on the text and contributes to the discourse purpose (Grosz and Sidner, 1986) of the article. |
| W04-0714 304 27:154 2 Centering Model In the centering theory (Grosz and Sidner, 1986; Grosz et al, 1995; Walker et al. , 1994; Strube and Hahn, 1996), the 'attentional state' was identified as a basic component of discourse structure that consisted of two levels of focusing: global and local. |
| C96-2101 305 6:174 1 Introduction Two general approaches can be distinguished in dialogue management: the structural approach, which uses a dialogue grammar to capture regularities of the dialogue in terms of exchanges and moves (Bilange, 1992; Cawsey, 1993; Grosz and Sidner, 1986), and the intention-based approach, which classifies the speaker's beliefs and intentions into speech acts, and uses planning operators to describe them (Appel% 1985; Allen and Perrault, 1980; Bunt et al. , 1984). |
| J89-3002 306 918:1172 Grosz and Sidner (1986) argue that coherence relations are not a useful analytical tool because no clear, closed set of them has been discovered. |
| J89-3002 307 770:1172 The Query System 5 NAIVE SEMANTICS AND DISCOURSE PHENOMENA 12 Most computational treatments of discourse phenomena acknowledge the role of world knowledge in anaphora resolution, temporal reasoning, and causal reasoning (Reichman 1985; Grosz and Sidner 1986; Wada and Asher 1986). |
| J89-3002 308 775:1172 The role of syntax and compositional semantics will be underplayed in what follows, only because these contributions have been thoroughly treated by others (Reinhart 1982; Asher and Wada 1988; Kamp 1981; Grosz and Sidner 1986; Reichman 1985; Webber 1985). |
| W99-0112 309 12:284 In order to cover coreference over discourse segments the centering model was extended by a stack mechanism (Grosz and Sidner, 1986). |
| W99-0112 310 73:284 Since a more general theory to referring expressions is needed, an extension is presented by Grosz and Sidner (1986). |
| P94-1002 311 50:190 The chains are used to structure texts according to the attentional/intentional theory of discourse structure (Grosz & Sidner 1986), and the extent of the chains correspond to the extent of a segment. |
| P94-1002 312 147:190 ogy that occurred in all of them reappears in this one location (in the spirit of a Grosz ~; Sidner (1986) "pop" operation). |
| N04-4035 313 10:103 This structure, in turn, identifies domains for interpretation; many systems for anaphora resolution rely on some notion of locality (Grosz and Sidner, 1986). |
| E99-1038 314 12:84 Defining focus: a eognito-pragmatie category The term focus has been used in various senses, at least six of which can be identified, i.e., phonological (Pierrehumbert, 1980; Ladd, 1996), semantic (Jackendoff, 1972; Prince, 1985), syntactic (Rochemont, 1986), cognitive (Sanford & Garrod, 1981; Musseler et al. , 1995), pragmatic (Halliday, 1967), and AI-focus (Grosz & Sidner, 1986) ~. |
| W04-2322 315 26:167 (Polanyi, 1985; Grosz and Sidner 1986; Webber, 1991) The LDM posits three structural relations between discourse units: 1. |
| W04-2322 316 11:167 2 The Classical Linguistic Discourse Model (C-LDM) Unlike the Discourse Structures Model (DSM) of Grosz and Sidner (1986), a pragmatic and psychological theory that aims to clarify the relationship between speakers intentions and their focus of attention in discourse, or the rhetorical model of Rhetorical Structures Theory (Mann and Thompson, 1988) that is designed to identify the coherence relations between segments of text, the Linguistic Discourse Model (LDM) (Polanyi and Scha, 1984; Polanyi, 1988; Polanyi and van den Berg, 1996) is a syntactically informed, semantically driven model developed to provide proper semantic interpretation for every utterance in a discourse despite the apparent discontinuities that are present even in well structured written texts. |
| J96-2004 317 71:99 Secondly, coding discourse and dialogue phenomena, and especially coding segment boundaries, may be inherently more difficult than many previous types of content analysis (for instance, 1 There are several variants of the kappa coefficient in the literature, including one, Scott's pi, which actually has been used at least once in our field, to assess agreement on move boundaries in monologues using action assembly theory (Grosz and Sidner 1986). |
| P97-1026 318 78:188 Second, entities differ in SALIENCE (Grosz and Sidner, 1986; Grosz et al. , 1995). |
| J99-3001 319 114:699 It is assumed that discourses are composed of constituent segments (Grosz and Sidner 1986), each of which consists of a sequence of utterances. |
| J99-3001 320 19:699 In a seminal paper, Grosz and Sidner (1986) wrapped up the results of their research and formulated a model in which three levels of discourse coherence are distinguished--attention, intention, and discourse segment structure. |
| J99-3001 321 694:699 In addition, an explicit relation to basic notions from speech act theory is also missing, though it should be considered vital for the global coherence of discourse (Grosz and Sidner 1986). |
| J99-3001 322 651:699 The centering model differs from these considerations in that it aims at unfolding a unified theory of discourse coherence at the linguistic, attentional, and intentional level (Grosz and Sidner 1986); hence, the search for a more principled, theory-based solution, but also the need for (almost) perfect linguistic analyses in terms of parsing and semantic interpretation. |
| W01-1605 323 45:189 While some take the elementary units to be clauses (Grimes, 1975; Givon, 1983; Longacre, 1983), others take them to be prosodic units (Hirschberg and Litman, 1993), turns of talk (Sacks, 1974), sentences (Polanyi, 1988), intentionally defined discourse segments (Grosz and Sidner, 1986), or the contextually indexed representation of information conveyed by a semiotic gesture, asserting a single state of affairs or partial state of affairs in a discourse world, (Polanyi, 1996, p.5). |
| W01-1605 324 7:189 However, rich theoretical approaches to discourse/text analysis (Van Dijk and Kintsch, 1983; Meyer, 1985; Grosz and Sidner, 1986; Mann and Thompson, 1988) have yet to be applied on a large scale. |
| J99-4006 325 1:160 Conceptions of Limited Attention and Discourse FocusBarbara J. Grosz t Harvard University Peter C. Gordon* University of North Carolina Walker (1996) presents a cache model of the operation of attention in the processing of discourse as an alternative to the focus space stack that was proposed previously by Grosz and Sidner (Grosz 1977a; Grosz and Sidner 1986). |
| J99-4006 326 115:160 In particular, as used in computer systems, stacks do not differentiate among different kinds of frames, but interruptions seem to operate differently from normal embeddings (Grosz and Sidner 1986) and there are open issues in explaining pronominal reference at discourse segment boundaries. |
| J99-4006 327 9:160 Walker presents as an alternative to the focus space stack previously proposed to model global attentional state (Grosz 1977a; Grosz and Sidner 1986) a cache model in which linear recency and a highly constrained cache capacity play primary roles. |
| J99-4006 328 56:160 In earlier work (Grosz 1977a; Grosz and Sidner 1986) we have argued that it is important to distinguish between two levels of discourse structure and processing: global and local. |
| C88-2099 329 60:204 Grosz & Sidner (1986) is the first unified approach in which the problem of segmentation is fled up with the notion of atten tional state. |
| C88-2099 330 41:204 Most such heuristics found in the iitera~ ture are syntactical in nature, relying, in almost Eliza-like fashion, on clue words and phrases (see references in Grosz & Sidner 1986: 177). |
| C88-2099 331 36:204 Webber 1987b), representing the narrative's unfolding contents; and the Current Focus Space, which is a collection of focusing mechanisms (including the deictic center) that together represent the "attentional state" (Grosz & Sidner 1986) of the system. |
| P07-1075 332 20:222 Third, the knowledge of textual structure helps to interpret the meaning of entities in a text (Grosz and Sidner 1986). |
| J00-2001 333 180:611 This model of text plans meshes well with the model of discourse structure developed by Grosz and Sidner (Grosz and Sidner 1985, 1986), in which the purpose of each discourse segment is an important part of the structure. |
| J04-3003 334 328:903 Unfortunately, discourse segments are difficult to identify reliably (Passonneau and Litman 1993), and Grosz and Sidner (1986) do not provide a specification of discourse intentions explicit enough that it can be used to identify the intentional structure of textswhich, according to Grosz and Sidner, determines their segmentation. |
| J04-3003 335 50:903 This claim, as well, is a basic tenet of much work on discourse (Sidner 1979; Prince 1981; Givon 1983; Gundel, Hedberg, and Zacharski 1993) and is supported by much psychological evidence (Hudson, Tanenhaus, and Dell 1986; Gernsbacher and Hargreaves 1988; Gordon, Grosz, and Gillion 1993; Stevenson, Crawley, and Kleinman 1994). |
| J04-3003 336 326:903 According to Grosz and Sidner (1986), centering is meant to capture preferences only within discourse segments. |
| J04-3003 337 14:903 Submission received: 16 April 2002; Revised submission received: 3 September 2003; Accepted for publication: 11 December 2003 310 Computational Linguistics Volume 30, Number 3 of attention and coherence in discourse (Grosz 1977; Sidner 1979; Grosz and Sidner 1986) concerned with local coherence and salience, that is, coherence and salience within a discourse segment. |
| J04-3003 338 150:903 Kameyama proposed that the local focus be updated after every tensed clause, not after every sentence, and classified tensed clauses into (1) utterances that constitute a permanent update of the local focus, such as coordinated clauses and adjuncts, and (2) embedded utterances that result in temporary updates that are then popped, much as the information introduced into discourse by subordinated discourse segments is popped according to Grosz and Sidner (1986). |
| C04-1020 339 13:199 Accounts of discourse structure vary greatly with respect to how many discourse relations they assume, ranging from two (Grosz & Sidner, 1986) to over 400 different coherence relations, reported in Hovy and Maier (1995). |
| C04-1020 340 23:199 2.1 Discourse segments Discourse segments can be defined as nonoverlapping spans of prosodic units (Hirschberg & Nakatani, 1996), intentional units (Grosz & Sidner, 1986), phrasal units (Lascarides & Asher, 1993), or sentences (Hobbs, 1985). |
| C04-1020 341 63:199 3 Data structures for representing coherence relations Most accounts of discourse coherence assume tree structures to represent coherence relations between discourse segments in a text (Carlson et al. , 2002; Corston-Oliver, 1998; Lascarides & Asher, 1993; Longacre, 1983; Grosz & Sidner, 1986; Mann & Thompson, 1988; Marcu, 2000; Polanyi, 1988; van Dijk & Kintsch, 1983; Walker, 1998; Webber et al. , 1999). |
| J97-1007 342 246:548 Grosz and Sidner (1986) claim that discourse segmentation is an important factor, though obviously not the only one, governing the use of referring expressions. |
| J97-1007 343 420:548 A possible solution would be to employ the concept of stacked focus space in Grosz and Sidner's discourse structure theory (Grosz and Sidner 1986; Dale 1992). |
| J97-1007 344 247:548 If the idea of context set were restricted to local focus space (Grosz and Sidner 1986), then the resulting descriptions would be to some extent sensitive to local aspects of discourse structure. |
| J97-1007 345 101:548 2.3 Rule 3: Adding Discourse Structure Grosz and Sidner (1986) suggest that three structures can be identified within a discourse: linguistic structure, intentional structure, and attentional state. |
| J97-1007 346 251:548 See Grosz and Sidner (1986) and Dale (1992) for some examples that illustrate this idea. |
| J97-1007 347 238:548 Dale (1992) used the global focus space (Grosz and Sidner 1986), as the context set in his domain of small discourse. |
| J97-1007 348 249:548 The beginnings of discourse segments, in a sense, indicate shifts of intention in a discourse (Grosz and Sidner 1986). |
| W97-0320 349 278:311 , e.g., Grosz & Sidner 1986; Nakhimovsky 1988). |
| W97-0320 350 18:311 Instead, the algorithm processes anaphoric references with respect to an Attentional State (Grosz & Sidner 1986) structured as a linear list of all times mentioned so far in the current dialog. |
| W97-0320 351 17:311 The algorithm does not include a mechanism for handling global focus (Grosz & Sidner 1986), for centering within a discourse segment (Sidner 1979; Grosz et al. 1995), or for performing tense and aspect interpretation. |
| W97-0320 352 256:311 6 Global Focus The algorithm is conspicuously lacking in any mechanism for recognizing the global structure of the discourse, such as in Grosz ~ Sidner (1986), Mann & Thompson (1988), Allen & Perranlt (1980), and their descendants. |
| P99-1024 353 121:216 Unlike in dialogue analyses carried out on completed dialogues (Grosz and Sidner, 1986), the dialogue manager needs to maintain a stack of all open discourse segments at each point in an on-going dialogue. |
| P99-1024 354 6:216 While we make no theoretical claims about the nature and structure of dialogue, we are influenced by the theoretical work of (Grosz and Sidner, 1986) and will use terminology from that tradition when appropriate. |
| P99-1077 355 8:92 Subsequent work has further developed this taxonomy (Hoey, 1991) and explored its implications in such are.as as paragraphing (Longacre, 1979; Bond and Hayes, 1984; Stark, 1988), relevance (Sperber and Wilson, 1995) and discourse structure (Grosz and Sidner, 1986). |
| A94-1020 356 80:148 Work on Discourse Structure Theory (Grosz, 1977; Grosz and Sidner, 1986) searches for automatic ways of segmenting discourse based on intentions and purposes embedded in discourse segments. |
| A94-1020 357 99:148 Following Grosz and Sidner (1986), segments occur in sequence, or are embedded, to allow users to elaborate on a change of focus before returning to the previous topic. |
| P96-1038 358 14:138 that discourse structural information can be inferred from orthographic cues in text, such as paragraphing and punctuation; from linguistic cues in text or speech, such as cue PHI~.ASES 1 (Cohen, 1984; Reichman, 1985; Grosz and Sidner, 1986; Passonneau and Litman, 1993; Passonneau and Litman, to appear) and other lexical cues (Hinkelman and Allen, 1989); from variation in referring expressions (Linde, 1979; Levy, 1984; Grosz and Sidner, 1986; Webber, 1988; Song and Cohen, 1991; Passonneau and Litman, 1993), tense, and aspect (Schubert and Hwang, 1990; Song and Cohen, 1991); from knowledge of the domain, especially for taskoriented discourses (Grosz, 1978); and from speaker intentions (Carberry, 1990; Litman and Hirschberg, 1990; Lochbaum, 1994). |
| P96-1038 359 32:138 Discourse structural elements were determined by experts in the Grosz and Sidner (1986) theory of discourse structure, based on either text alone or text and speech. |
| P96-1038 360 50:138 3.3 Discourse Segmentation In our research, the Grosz and Sidner (1986) theory of discourse structure, hereafter G&S, provides a foundation for segmenting discourses into constituent parts. |
| P98-1103 361 43:182 3 The Topic Model In AI-based dialogue modelling, topics are associated with a particular discourse entity, focus, which is currently in the centre of attention and which the participants want to focus their actions on, e.g. Grosz and Sidner (1986). |
| W08-0101 362 15:190 Yet, as conversational analysts focused on micro-levels of dialogue such as turntaking, computational linguists uncovered and formalized macro-level dialogue structure and devised well-defined representations of semantics for at least some forms of dialogues (Allen and Perrault, 1980; Grosz and Sidner, 1986; Clark, 1996), which have in turn been implemented in spoken dialogue systems (Rich and Sidner, 1998; Allen et al., 2005). |
| W02-0226 363 134:218 6 Grosz and Sidner (1986) proposed a tripartite discourse model consisting of attentional state, intentional structure, and linguistic structure. |
| J88-2004 364 321:535 Grosz and Sidner 1986). |
| P98-2188 365 42:146 Researchers in discourse, such as Grosz and Sidner (1986), Lambert (1993), Hirschberg and Litman (1993), Chen (1995), Andernach (1996), Samuel (1996), and Chu-Carroll (1998) have suggested several features that might be relevant for the task of computing dialogue acts. |
| J88-3009 366 63:68 Grosz and Sidner (1986) discuss how DMs are built up, and Chin (1986), Litman and Allen (1984), Carberry (1983), and Allen and Perrault (1980), among others, discuss this process for different aspects of UMs. |
| J88-3009 367 2:68 A discourse model (DM) contains information about the conversation, such as the linguistic structure, the attentional state, and the intentional structure \[Grosz and Sidner 1986). |
| W04-1115 368 13:157 This structure, in turn, identifies domains for interpretation; many systems for anaphora resolution rely on some notion of locality (Grosz and Sidner, 1986). |
| D08-1100 369 49:258 More complicated dialog representations (Grosz and Sidner, 1986; Litman and Allen, 1987) model several aspects of a dialog including domain-specific information. |
| P93-1020 370 33:260 Grosz and Hirschberg (Grosz and Hirschberg, 1992; Hirschberg and Grosz, 1992) asked subjects to structure three AP news stories (averaging 450 words in length) according to the model of Grosz and Sidner (1986). |
| P93-1020 371 9:260 The segmental structure of discourse has been claimed to constrain and be constrained by disparate phenomena: cue phrases (Hirschberg and Litman, 1993; Gross and Sidner, 1986; Reichman, 1985; Cohen, 1984); lexical cohesion (Morris and Hirst, 1991); plans and intentions (Carberry, 1990; Litman and Allen, 1990; Gross and Sidner, 1986); prosody (Grosz and Hirschberg, 1992; Hirschberg and Gross, 1992; Hirschberg and Pierrehumbert, 1986); reference (Webber, 1991; Gross and Sidner, 1986; Linde, 1979); and tense (Webber, 1988; Hwang and Schubert, 1992; Song and Cohen, 1991). |
| P93-1020 372 45:260 Morris and Hirst (1991) structured a set of magazine texts using the theory of Grosz and Sidner (1986). |
| P93-1020 373 54:260 A number of alternative proposals have been presented which directly or indirectly relate segments to intentions (Grosz and Sidner, 1986), RST relations (Mann et al. , 1992) or other semantic relations (Polanyi, 1988). |
| W99-0313 374 86:187 Following (Grosz and Sidner, 1986), macro-level analysis captures two fundamental intentional relations between I-units, those of domination (or parent-child) and satisfactionprecedence (or sibling) relations. |
| W99-0313 375 26:187 The second scheme concerned intentional/informational structure (Grosz and Sidner, 1986; Nakatani et al. , 1995) as content, operated at a macro level of granularity, and was structured as hierarchical trees (with annotations for capturing discontinuities). |
| P96-1009 376 171:301 It maintains a discourse state that consists of a goal stack with similarities to the plan stack of Litman & Allen (1987) and the attentional state of Grosz & Sidner (1986). |
| E95-1033 377 156:371 Our exposition builds on the well-known focusing mechanism (Sidner, 1983; Grosz and Sidner, 1986). |
| W00-0310 378 9:121 2 Theoretical Foundations In this work, we implement and extend the compositional theory of intonational meaning proposed by Pierrehumbert and Hirschberg (1986; 1990), who sought to identify correspondences between the Bell Laboratories, Lucent Technologies 600 Mountain Avenue Murray Hill, NJ 07974 USA {chn I j encc}research, bell-labs, com Grosz and Sidner (1986) computational model of discourse interpretation and Pierrehumbert's prosodic grammar for American English (1980). |
| A92-1040 379 21:55 Following Grosz and Sidner (1986) we distinguish linguistic structure, attentional, or belief structure, and intelltionM structure. |
| P91-1025 380 130:232 reference time = the time pivot of the linguistic SOur characterization of the context of utterance draws on a number of existing approaches to discourse representation and discourse processing, most notably those of Grosz and Sidner (1986), Discourse Representation Theory (Kamp 1981, Helm 1982), Situation Semantics (Barwise and Perry 1983, Gawron and Peters 1990), and Linguistic Discourse Model (Scha and Polanyi 1988). |
| P91-1025 381 147:232 llThis parameter may be tied to the "intentional" aspect of discourse as proposed by Grosz and Sidner (1986). |
| W97-1408 382 27:163 This is similar to the set of entities in the focus spaces of the discourse focus stack in Grosz and Sidner's theory of discourse structure (Grosz, Sidner, 1986). |
| W99-0113 383 52:201 Roberts (1998) argues that C0 is an unordered setof backward-looking centers in terms of classical Discourse Representation Theory notions of familiarity, compatibility and logical accessibility (Kamp 1981, Helm 1982, Kamp and Reyle 1993, Asher 1993), with an additional constraint that the set of discourse referents are attentionally accessible, a notion taken from Grosz and Sidner (1986). |
| J05-2005 384 21:651 Going beyond the question of how different informational-level accounts can be compatible with each other, Moser and Moore (1996) discuss the compatibility of rhetorical structure theory (RST) (Mann and Thompson 1988) with the theory of Grosz and Sidner (1986). |
| J05-2005 385 14:651 Some accounts aim to represent the intentional-level structure of a discourse; in these accounts, coherence relations reflect how the role played by one discourse segment with respect to the interlocutors intentions relates to the role played by another segment (e.g. , Grosz and Sidner 1986). |
| J05-2005 386 294:651 Grosz and Sidner 1986), which Knott argues are less constrained, than in terms of rhetorical relations (cf. |
| J05-2005 387 42:651 Whereas some argue that discourse segments should be prosodic units (Hirschberg and Nakatani 1996), others argue for intentional units (Grosz and Sidner 1986), phrasal units (Lascarides and Asher 1993; Longacre 1983; Webber et al. 1999), or sentences (Hobbs 1985). |
| J05-2005 388 247:651 Data Structures for Representing Coherence Relations In order to represent the coherence relations between discourse segments in a text, most accounts of discourse coherence assume tree structures (Britton 1994; Carlson, Marcu, and Okurowski 2002; Corston-Oliver 1998; Longacre 1983; Grosz and Sidner 1986; Mann and Thompson 1988; Marcu 2000; Polanyi and Scha 1984; Polanyi 1996; Polanyi et al. 2004; van Dijk and Kintsch 1983; Walker 1998); some accounts do not allow crossed dependencies but appear to allow nodes with multiple parents (Lascarides and Asher 1991). |
| J05-2005 389 16:651 Furthermore, accounts of discourse structure vary greatly with respect to how many discourse relations they assume, ranging from 2 (Grosz and Sidner 1986) to over 400 different coherence relations (reported in Hovy and Computer Laboratory and Genetics Department, Cambridge, CB3 0FD, U.K. E-mail: Florian.Wolf@cl.cam.ac.uk Department of Brain and Cognitive Sciences, Cambridge, MA 02139. |
| J05-2005 390 22:651 However, note that Moser and Moore (1996) focus on the question of how compatible the claims are that Mann and Thompson (1988) and Grosz and Sidner (1986) make about intentional-level discourse structure. |
| J97-1002 391 33:406 Transactions are made up of conversational games, which are often also called dialogue games (Carlson 1983; Power 1979), interactions (Houghton 1986), or exchanges (Sinclair and Coulthard 1975), and show the same structure as Grosz and Sidner's discourse segments (1986) when applied to task-oriented dialogue. |
| P98-2145 392 10:171 Therefore, identifying segment boundaries in a text is considered as a first step to construct the discourse structure(Grosz and Sidner, 1986). |
| W06-2708 393 31:66 Generally speaking, the structure of tutorial dialogue is governed by the task structure just as in task-oriented dialogue (Grosz and Sidner, 1986). |
| W02-0105 394 48:67 And, having thus introduced stacks, we then investigated the Grosz and Sidner (1986) stack-based theory of discourse structure, showing that language structures exist at granularities beyond the sentence level. |
| P03-1071 395 119:177 5.2 Features Cue phrases: previous work on segmentation has found that discourse particles like now, well provide valuable information about the structure of texts (Grosz and Sidner, 1986; Hirschberg and Litman, 1994; Passonneau and Litman, 1997). |
| P03-1071 396 35:177 (Grosz and Sidner, 1986)) are generally considered to be difficult to mark reliably. |
| C04-1034 397 102:212 3 The DAR Algorithm 3.1 Search Space and DE lists dar presupposes the discourse structure described by Grosz and Sidner (1986). |
| W00-1425 398 9:222 In the theory of discourse structure developed by Grosz and Sidner (1986), each discourse segment exhibits two types of coherence: local coherence among utterances inside the segment, and global coherence between this segment and other discourse segments. |
| P97-1025 399 29:219 Following (Grosz and Sidner, 1986) we further assume that every posting of a new task by the hierarchical planning mechanism creates new attentional spaces. |
| P97-1025 400 102:219 Igroup(F, *) A subgroup(U, F, *) A unit(F, 1, *) A unit(U, lt\], *) :=~ 1 = It\] Reason (Hyp) (Def-subgroup 7) (Def-unit 7) (::1 9) (Hyp) (Def-unit 7 11) (Def-subset 8 11) (Def-subset 8 9) (Def-group 7) (Def-sohition 12 13 14 15) (Def-unit 7 13) (Def-unit 7) (Def-soluti0n 13 17 18 15) (Th-solution 17 16 19) (Choice 10 20) (Ded 7:21) Figure 3: Abstracted Proof about Unit Element of Subgroups of a discourse into an attentional hierarchy, since following the theory of Grosz and Sidner (Grosz and Sidner, 1986), there is a one-to-one correspondence between the intentional hierarchy and the attentional hierarchy. |
| P97-1025 401 25:219 Despite this difference, the choices to be made here have much in common with the choices of subsequent references discussed in more general frameworks (Reichman, 1985; Grosz and Sidner, 1986; Dale, 1992): they depend on the availability of the object to be referred to in the context and are sensitive to the segmentation of a context into an attentional hierarchy. |
| P94-1006 402 45:232 Grosz and Sidner's (1986) model of discourse interpretation is one where the same discourse elements are related simultaneously on the informational and intentional levels. |
| P89-1016 403 155:179 These systems currently have no means for identifying basic discourse elaborations and, to date, they have not incorporated discourse structural cues which could be helpful in signaling the relationship of discourse segments (Grosz & Sidner, 1986; Litman & Allen, 1989; Oviatt & Cohen, 1989; Reichman, 1978). |
| P07-1128 404 11:162 Second, because the automatically generated segments make up for the lack of explicit orthographic cues (e.g. , story and paragraph breaks) in conversational speech, dialogue segmentation is useful in many spoken language understanding tasks, including anaphora resolution (Grosz and Sidner, 1986), information retrieval (e.g. , as input for the TREC Spoken Document Retrieval (SDR) task), and summarization (Zechner and Waibel, 2000). |
| P97-1014 405 38:262 Table h Transition Types As a working hypothesis, for the purposes of anaphora resolution we subscribe to Walker's model, in particular to that part which casts doubt on the hypothesized dependency of the attentional from the intentional structure of discourse (Grosz & Sidner, 1986, p. 180). |
| P97-1014 406 26:262 This finding precludes a reliable prediction of segment boundaries based on the occurrence of 1 Our notion of referential discourse segment should not be confounded with the intentional one originating from Grosz & Sidner (1986), for reasons discussed in Section 2. |
| J95-1002 407 121:801 There is considerable debate in the field of discourse analysis concerning the relative importance of intentional structure and rhetorical relations (e.g. , Grosz and Sidner 1986; Moore and Pollack 1992), most systems focusing on one or the other. |
| W04-2323 408 8:226 1 Introduction The linguistic structure of a discourse is composed of utterances that exhibit meaningful hierarchical relationships (Grosz and Sidner, 1986). |
| W04-2323 409 145:226 The monologues were subsequently annotated by a group of subjects according to the Grosz and Sidner (1986) theory of discourse structure. |