Elamur Research⌕
☰
home / papers / 2004 / Pronominal and Sortal Anaphora Resolution for Biomedical Literature

Pronominal and Sortal Anaphora Resolution for Biomedical Literature

Summary

The paper addresses automatic resolution of the two anaphora types most frequent in biomedical abstracts. The first is pronouns such as it, they and their. The second is sortal (definite) noun phrases, for example "these proteins", that point back to earlier biomedical entities. The authors' pipeline works in four steps:

  • It POS-tags and chunks the text.
  • It assigns grammatical roles with extended Siddharthan-style rules, including coordination rules for plural antecedents.
  • It removes pleonastic "it" and definite NPs that fall outside biomedical UMLS classes.
  • It enforces number agreement.

Candidates from the two preceding sentences are then ranked by a salience score that mixes syntactic cues (recency, role preference and agreement, number) with semantic cues (LCS, UMLS semantic type agreement, biomedical antecedent). Semantic compatibility for pronouns relies on SA/AO patterns mined from GENIA 3.02p. For words missing from UMLS, the system uses headwords harvested from UMLS synonyms plus PubMed hit statistics. A genetic algorithm picks the best feature subset. On Medstract, the system reaches about 92% F-score for pronominal and 78% for sortal anaphora, outperforming Castaño et al. This matters for downstream relation extraction from MEDLINE.

Key points

  • Resources used: UMLS 2003AC Metathesaurus, GENIA 3.02p (source of SA/AO patterns), WordNet 2.0 (hyponym matching) and PubMed query statistics.
  • Evaluation data:
    • Medstract: 32 MEDLINE abstracts with 83 anaphora pairs (26 pronominal, 57 sortal).
    • An additional in-house set of 103 MEDLINE abstracts with 177 pronominal pairs.
  • Results on Medstract:
    • The best-fit strategy with GA-selected features scored 92.31% F (pronominal) and 78.26% F (sortal).
    • Castaño et al. scored 75.23% and 74.4% respectively.
    • Nearest-fit was clearly weaker.
  • Syntactic features (F1–F4) help pronoun resolution but matter little for sortal anaphora. Semantic features (LCS, semantic type agreement, biomedical antecedent) are crucial for sortal anaphora.
  • Headword mining is the key aid for unknown words. Sortal F-score was 78% with both headwords and PubMed, 76% with headwords only, and about 58–59% without headwords. PubMed statistics added only a small gain.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Linguistics & languages

Topics: Coreference resolution

Cited by

5 papers of our library cite it (of the 140673 whose bibliographies we read); 2 of them have a page here, 3 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work.

@inproceedings{lin2004pronominal,
  title = {{Pronominal and Sortal Anaphora Resolution for Biomedical Literature}},
  author = {Lin, Yu-Hsiang and Liang, Tyne},
  booktitle = {Proceedings of the 16th Conference on Computational Linguistics and Speech Processing},
  year = {2004},
  url = {https://aclanthology.org/O04-1011/}
}

References

17 references, 7 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. [ 1] Breck Baldwin, “CogNIAC: high precision coreference with limited knowledge and linguistic resources,” In Proceedings of the ACL'97/EACL'97 workshop on Operational factors in practical, robust anaphora resolution, 1997, pp. 38-45. find our card
  2. [ 2] José Castaño, Jason Zhang, Hames Pustejovsky, “Anaphora Resoution in Biomedical Literature,” In International Symposium on Reference Resolution, 2002 find
  3. [ 3] Ido Dagan and Alon Itai, “Automatic processing of large corpora for the resolution of anaphora references,” In Proceedings of the 13th International Conference on Computational Linguistics (COLING'90), Vol. III, 1-3, 1990. find our card
  4. [ 4] Michel Denber, “Automatic resolution of anaphora in English,” Technical report, Eastman Kodak Co. , 1998. find
  5. [ 5] Udo Hahn and Martin Romacker, “Creating Knowledge Repositories from Biomedical Reports:The MEDSYNDIKATE Text Mining System, “In Pacific Symposium on Biocomputing, 2002 find
  6. [ 6] J. Hobbs, “Pronoun resolution,” Research Report 76-1, Department of Computer Science, City College, City University of New York, August 1976 find
  7. [ 7] R. Gaizauskas, G. Demetriou, P.J. Artymiuk and P. Willett, “Protein Structures and Information Extraction from Biological Texts: The PASTA System,” In Bioinformatics 2003 find
  8. [ 8] Christopher Kennedy and Branimir Boguraev, “Anaphora for everyone: Pronominal anaphora resolution without a parser,” In Proceedings of the 16 th International Conference on Computational Linguistics, 1996, pp.113-118. find our card
  9. [ 9] Shalom Lappin and Herbert Leass, “An Algorithm for Pronominal Anaphora Resolution,” Computational Linguistics, Volume 20, Part 4, 1994, pp. 535-561. find our card
  10. [10] Tyne Liang and Dian-Song Wu, “Automatic Pronominal Anaphora Resolution in English Texts,” In Computational Linguistics and Chinese Language Processing Vol.9, No.1, 2004, pp. 21-40 find our card
  11. [11] Ruslan Mitkov, “Robust pronoun resolution with limited knowledge, “ In Proceedings of the 18th International Conference on Computational Linguistics (COLING'98)/ACL'98 Conference Montreal, Canada. 1998, pp. 869-875. find our card
  12. [12] Ruslan Mitkov, “Anaphora Resolution: The State of the Art,” Working paper (Based on the COLING'98/ACL'98 tutorial on anaphora resolution), 1999. find
  13. [13] Ruslan Mitkov and Catalina Barbu, “Evaluation tool for rule-based anaphora resolution methods,” In Proeedings of ACL'01, Toulouse, 2001. find our card
  14. [14] Ruslan Mitkov, Richard Evans and Constantin Orasan, “A new fully automatic version of Mitkov's knowledge-poor pronoun resolution method,” In Proceedings of CICLing- 2000, Mexico City, Mexico. find
  15. [15] T. Ohta, Y. Tateisi, J.D. Kim, S.Z. Lee and J. Tsujii. “GENIA corpus: A Semantically Annotated Corpus in Molecular Biology Domain.” In the Proceedings of the ninth International Conference on Intelligent Systems for Molecular Biology (ISMB 2001) poster session. pp. 68. 2001. find
  16. [16] James Pustejovsky, Anna Rumshisky, José Castaño, ” Rerendering Semantic Ontologies: Automatic Extensions to UMLS through Corpus Analytics,” LREC 2002 Workshop on Ontologies and Lexical Knowledge Bases, 2002. find
  17. Without Headword 59% 58% [17] J. Pustejovsky, José Castaño, J. Zhang, B. Cochran, M. Kotecki, ” Robust Relational Parsing over Biomedical Literature: Extracting Inhibit Relations.,” In Pacific Symposium on Biocomputing, 2002 find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/papers/lin-2004-pronominal-sortal-anaphora-resolution-biomedical/