Paper: Species Disambiguation for Biomedical Term Identification
Webmaster's Note:
The whole dataset is available Here. Please download the dataset instead of crawling the website.
Basic Info:
Abstract
An important task in information extraction
(IE) from biomedical articles is term iden-
tification (TI), which concerns linking en-
tity mentions (e.g., terms denoting proteins)
in text to unambiguous identifiers in stan-
dard databases (e.g., RefSeq). Previous work
on TI has focused on species-specific docu-
ments. However, biomedical documents, es-
pecially full-length articles, often talk about
entities across a number of species, in which
case resolving species ambiguity becomes an
indispensable part of TI. This paper de-
scribes our rule-based and machine-learning
based approaches to species disambiguation
and demonstrates that performance of TI can
beimprovedbyover20%ifthecorrectspecies
are known. We also show that using the
speciespredictedbytheautomaticspeciestag-
gers can improve TI by a large margin.
Statistics Summary
| Stat | Rank | Value |
|---|
| Incoming Citations | 0(0) | 0(0) |
| Outgoing Citations | 9489(8582) | 1(1) |
| PageRank | 7455 | 23 |
| PageRank per Year | 620 | 23 |
Incoming Citations
| Id | Title |
|---|
| None | No Incoming Citations |
| ID | Title | Num Co-citations |
Citation Summary
| Citing sentences |
|---|
Summary
| Summary extracted from citation sentences |
|---|