Citation Summary
| Citing sentences |
|---|
| A97-1010 1 17:197 That is, it tries to detect and correct speech repairs automatically using text alone Hindle (1983) adds rules to a deterministic parser to tackle the problem of correcting speech repairs. |
| J97-1005 2 425:736 A feasibility study of the parsers CASS (Abney 1990) and FIDDITCH (Hindle 1983) showed that coding FICUs on this data could be automated, n Subjectivity in coding the infer feature was eliminated by providing operational definitions of 11 Specifications for adapting the parser and incorporating it into coding software were formulated, but never implemented. |
| P99-1053 3 10:187 (Hindle, 1983) and (Bear et al. , 1992) performed speech repair identification in their parsers, and removed the corrected material (reparandum) from consideration. |
| P99-1053 4 11:187 (Hindle, 1983) states that repairs are available for semantic analysis but provides no details on the representation to be used. |
| W99-0909 5 27:183 An example of another approach to doing this is the Fidditch parser of Hindle (Hindle, 1983) (based on the deterministic parser of Marcus (Marcus, 1980)), which was used to annotate the Penn Treebank (Marcus et al. , 1993). |
| P92-1008 6 36:192 To mark the site of a repair, corresponding to Hindle's "edit signal" (Hindie, 1983), we use a vertical bar (I)To express the notion that words on one side of the repair correspond to words on the other, we use a combination of a letter plus a numerical index. |
| P92-1008 7 15:192 Hindle (1983) attempts to delimit and correct repairs in spontaneous human-human dialog, based on transcripts containing an "edit signal," or external and reliable marker at the "expunction point," or point of interruption. |
| P99-1052 8 36:193 These decisions may be in conflict with much of the literature on robust parsing (e.g. , (Hindle, 1983; Hipp, 1993; Heinecke et al. , 1998)), but the alternative of relaxing the parsing constraints would appear to be a dead end in the context of the VERBMOBIL architecture. |
| C94-1098 9 17:160 I~ELATED WORKS (Hindle 1983) and (Langer 1990) proposed parsers coping with self-repaired utterances. |
| A00-1026 10 33:141 The output produced is in the tradition of partial parsing (Hindle 1983, McDonald 1992, Weischedel et al. 1993) and concentrates on the simple noun phrase, what Weischedel et al. |
| P94-1041 11 51:309 Hindle (1983) addressed the problem of correcting selfrepairs by adding rules to a deterministic parser that would remove the necessary text. |
| A94-1018 12 17:154 Otherthan syntactic knowledge includes grammar specific recovery rules such as recta-rules (Weishedel and Sondheimer, 1983), semantic or pragmatic knowledge which may depend on a particular domain (Carbonell and Hayes, 1983) or the characteristics of the ill-formed utterances observed in human discourse (Hindle, 1983). |
| H05-1030 13 34:172 Most prior work has focused on handling disfluencies and continued to rely on hand-annotated transcripts that include punctuation, case, and known sentence boundaries (Hindle, 1983; Core and Schubert, 1999; Charniak and Johnson, 2001; Engel et al. , 2002). |
| J93-2005 14 368:423 Hindle (1990) reports interesting results of this kind based on literal collocations, where he parses the corpus (Hindle 1983) into predicate-argument structures and applies a mutual information measure (Fano 1961; Magerman and Marcus 1990) to weigh the association between the predicate and each of its arguments. |
| P00-1001 15 47:157 Few approaches to parsing have tried to handle disfluent utterances (notable exceptions are Core & Schubert, 1999; Hindle, 1983; Nakatani & Hirschberg, 1994; Shriberg, Bear, & Dowding, 1992). |
| H89-1018 16 52:174 Hindle (1983) processed transcripts of speech using a Mracusstyle parser. |
| P89-1016 17 11:179 Furthermore, it has become clear that the algorithms and heuristics needed to design spoken language systems will be different from those required for keyboard system s (Cohen, 1984; Hindle, 1983; Oviatt & Cohen, 1988 ~: 1989; Ward, 1989). |
| H94-1042 18 19:140 There is currently a upsurge in research in partial parsing in the natural language community (e.g. , Hindle 1983, Weischedel, et al. 1991), where rather than building a single syntactic tree for each sentence, a forest is returned, and phrases outside the coverage of the grammar and unknown words are systematically ignored. |
| J99-4003 19 104:812 This is especially true for repairs, since their occurrence disrupts the local context that is needed to determine the POS tags (Hindle 1983). |
| J99-4003 20 431:812 Hindle (1983) and Kikui and Morimoto (1994) both separate the task of correcting a repair from detecting it by assuming that there is an acoustic editing signal that marks the interruption point of speech repairs (as well as access to the POS tags and utterance boundaries). |
| J99-4003 21 463:812 Since speech repairs are often accompanied by word correspondences (Levelt 1983; Hindle 1983; Bear, Dowding, and Shriberg 1992; Heeman and Allen 1994; Kikui and Morimoto 1994), the actual reparandum will better predict the words in the alteration of the repair. |
| J99-4003 22 455:812 Probably the most widely used is the presence of word correspondences between the reparandum and alteration, both at the word level and at the level of syntactic constituents (Levelt 1983; Hindle 1983; Bear, Dowding, and Shriberg 1992; Heeman and Allen 1994; Kikui and Morimoto 1994). |
| J99-4003 23 96:812 Hindle 1983; Levelt 1983), as the following example illustrates. |
| J99-4003 24 55:812 Following loosely in the footsteps of the work of Hindle (1983), we divide them into the following categories: fresh starts, modification repairs, and abridged repairs. |
| J84-2002 25 85:903 (Chafe 1982); and spoken language exhibits regular patterns of false starts and hesitations (Hindle 1983, Kroch and Hindle 1982). |
| J84-2002 26 13:903 Previous investigations have concentrated on syntactic differences between spoken and written language (Hindle 1983, Kroch and Hindle 1982, Thompson 1980), with the goal of adapting parsing techniques to handle the syntax of spoken language. |
| P89-1015 27 81:224 To use the tagged Brown Corpus for training and IMore recent approaches to deter~i-i~tic parsing may allow categorial disamhiguation to occur ~fler some of the syntactic properties of phrases are noted (Marcus, Hindle, and Fleck 1983). |
| P89-1015 28 40:224 Fidditch is one such deterministic parser, designed to provide a syntactic analysis of text as a tool for locating examples of various linguisticaUy interesting structures (Hindle 1983). |
| A92-1027 29 208:253 And it appears that something like this scheme is used in Hindle's FIDDITCH parser (partially described in Hindle 1983). |
| C00-2125 30 24:122 (Hindle 1983) 1.2 Gramnmr-Oriented Production of Gernmn Speech Repairs German, an Indo-Europcan language, is a language with a strong emphasis on grammatical flexion. |
| C00-2125 31 8:122 In addition, studies have shown that syntactic and prosodic features of spontaneous speech data provide empirical evidence with regard to reflecting the speaking habits of speakers, and also help to develop better parsing strategies and natural language processing systems (Heeman and Allen 1999, Hindle 1983). |
| N04-4040 32 141:144 Techniques using parse trees to identify disfluencies have shown success in the past (Hindle, 1983). |
| W00-0506 33 12:200 Linguistically and stylistically they differ from written language: sentences are shorter and poorly structured, and contain idiomatic expressions, ungrammaticality, etc. The associated difficulties stem from the inherently colloquial nature of closed captions, and, to different degrees, of all forms of transcribed speech (Hindle, 1983). |
| J90-1003 34 104:232 7 PREPROCESSING WITH A PARSER Hindle (Church et al. 1989) has found it helpful to preprocess the input with the Fidditch parser (Hindle 1983a, 1983b) to identify associations between verbs and arguments, and postulate semantic classes for nouns on this basis. |
| P97-1033 35 28:203 However, speech repairs disrupt the context that is needed to determine the POS tags (Hindle, 1983). |
| P97-1033 36 56:203 Example 4 (d92a-l.3 utt65) so that will total will take seven hours to do that reparandumT alteration interruption point 1This classification is similar to that of Hindle (1983) and Levelt (1983). |
| P97-1033 37 15:203 (Hindle, 1983; Bear, Dowding, and Shriberg, 1992; Nakatani and Hirschberg, 1994; Heeman and Allen, 1994; Stolcke and Shriberg, 1996b)). |
| P06-1021 38 81:158 The 1McKelvies metarule approach declaratively expresses Hindles (1983) Stack Editor and Category Copy Editor rules. |
| P93-1007 39 16:214 Although studies of large speech corpora have found that approximately 10% of spontaneous utterances contain disfluencies involving self-correction, or REPAIRS (Hindle, 1983; Shriberg et al. , 1992), little is known about how to integrate repair processing with real-time speech recognition. |
| P93-1007 40 49:214 Importantly, Hindle's system allows for nonsurface-based corrections and sequential application of correction rules (Hindle, 1983, p. 123). |
| P93-1007 41 45:214 An hypothesized acousticphonetic edit signal, "a markedly abrupt cut-off of the speech signal" (Hindle, 1983, p.123), is assumed to mark the interruption of fluent speech (cf. |
| P93-1007 42 43:214 One proposal for repair processing that lends itself to both incremental processing and the integration of speech cues into repair detection is that of Hindle (1983), who defines a typology of repairs and associated correction strategies in terms of extensions to a deterministic parser. |
| P93-1007 43 20:214 RIM builds upon Labov (1966) and Hindle (1983) by conceptually extending the EDIT SIGNAL HYPOTHESIS -that repairs are acoustically or phonetically marked at the point of interruption of fluent speech. |
| P93-1007 44 66:214 RIM incorporates two main assumptions of Hindle (1983): (1) correction strategies are linguisticallyrulegoverned, and (2) linguistic cues must be available to signal when a disfluency has occurred and to 'trigger' correction strategies. |