Elamur Research⌕
☰
home / papers / 2000 / Multilingual Coreference Resolution

Multilingual Coreference Resolution

Summary

The paper asks whether aligned bilingual text can improve identity coreference resolution, the MUC-style task of linking nouns, pronouns and noun phrases to their antecedents. The authors had native speakers produce Romanian translations of the coreference training texts from MUC-6 and MUC-7. Where possible, they reused the English coreference identifiers. Their starting point is COCKTAIL, a knowledge-poor resolver that applies priority-ordered heuristics mined from annotated data. Its training data was enlarged automatically by enumerating every coreference structure that yields the same chain. SWIZZLE extends COCKTAIL. It runs the resolver on both languages and compares the results across aligned expressions. When the resolutions disagree, it adds, reprioritizes or removes heuristics, for example when the antecedents are not translations of each other or one antecedent opens a new chain. Scored with the official MUC scorer, SWIZZLE raised precision in both languages. Recall fell slightly, because unreliable links were discarded. The work matters because translations can supply extra coreference cues: Romanian referential expressions help resolve difficult English cases.

Key points

  • Overall precision rose from 84% to 87% for English and from 72% to 76% for Romanian. Overall recall dropped from 78% to 77% for English and from 72% to 70% for Romanian. These figures come from tables that were garbled in the PDF extraction.
  • Data expansion: the 1,626 MUC-6 and 2,245 MUC-7 coreference relations grew to 6,095,142 and 8,269,403 relations respectively. The authors report an expansion factor of 3,710. Average chain lengths are 7.21 for MUC-6 and 8.57 for MUC-7.
  • In the ideal case, both antecedents are translations of each other. This held for 63.3% of MUC-6 references and 58.7% of MUC-7 references, and over half of these cases are pronouns or named entities.
  • COCKTAIL handles five pronoun types and three nominal forms. Its heuristics fall into three classes: strong indicators, semantic consistency checks using WordNet and Treebank statistics, and coercion via morphology, meronyms and hypernyms.
  • In 64% of cases, the English link was resolved by a higher-priority heuristic than its Romanian counterpart. The authors use this to explain why English precision gained more.

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

15 papers of our library cite it (of the 140673 whose bibliographies we read); 7 of them have a page here, 8 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.3115/974147.974167

@inproceedings{harabagiu2000multilingual,
  title = {{Multilingual Coreference Resolution}},
  author = {Harabagiu, Sanda M. and Maiorano, Steven J.},
  booktitle = {Sixth Applied Natural Language Processing Conference},
  year = {2000},
  doi = {10.3115/974147.974167},
  url = {https://doi.org/10.3115/974147.974167}
}

References

22 references, 9 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Douglas E. Appelt, Jerry R. Hobbs, John Bear, David Israel, Megumi Kameyama and Mabry Tyson. 1993. The SRI MUC-5 JV-FASTUS Information Extraction System. In Proceedings of the Fifth Message Understanding Conference (MUC-5). find
  2. Brack Baldwin. 1997. 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, pages 38-45, Madrid, Spain. find our card
  3. Andrei Bantam. 1969. Dic~ionar Rom£n-Englez, Enlgez-Romfi~. Editura ~tiin~ific~, Bucure~ti. find
  4. David Bean and Ellen Riloff. 1999. Corpus-Based Identification of Non-Anaphoric Noun Phrases. In Proceedings of the 37th Conference of the Assosiation for Computatioanl Linguistics (A CL-99), pages 373-380. find our card
  5. Eric Brill. A simple rule-based part of speech tagger. In Proceedings of the Third Conference on Applied Natural Language Processing, pages 152-155, 1992. find
  6. Joseph F. Cameron-Jones and Ross Quinlan. 1993. Avoiding Pitfalls When Learning Recursive Theories. In Proceedings of the 13th International Joint Conference on Artificial Intelligence (IJCAI-93), pages 1050-1055. find
  7. Claire Cardie and Kiri Wagstaff. 1999. Noun phrase coreference as clustering. In Proceedings of the Joint Conference on Empirical Methods in NLP and Very Large Corpora, pages 82-89. find our card
  8. Niyu Ge, John Gale and Eugene Charniak. Anaphora Resolution: A Multi-Strategy Approach. In Proceedings of the 6th Workshop on Very Large Corpora, (COLING/A CL '98). find our card
  9. Ido Dagan and Ken W. Church. 1994. TERMIGHT: Identifying and translating technical terminology. In Proceedings of the ~th ACL Conference on Applied Natural Language Processing (ANLP-94). find
  10. Sanda M. Harabagiu. 1999. Lexical Acquisition for a Romanian WordNet. Proceeding of the 3rd European Summer School on Computational Linguistics. find
  11. Sanda M. Harabagiu and Steve J. Maiorano. 1999. Knowledge-Lean Coreference Resolution and its Relation to Textual Cohesion and Coherence. In Proceedings of the Workshop on the Relation of Discourse/Dialogue Structure and Reference, ACL'98, pages 29-38. find
  12. Jerry R. Hobbs. Resolving pronoun references. Lingua, 44:311-338. find our card
  13. Andrew Kehler. 1997. Probabilistic Coreference in Information Extraction. In Proceedings of the Second Conference on Empirical Methods in Natural Language Processing (SIGDAT), pages 163-173. find our card
  14. Shalom Lappin and Herbert Leass. 1994. An algorithm for pronominal anaphora resolution. Computational Linguistics, 20(4):535-562. find our card
  15. Rosie Jones, Andrew McCallum, Kevin Nigam and Ellen Riloff. 1999. Bootstrapping for Text Learning Tasks. In Proceedings of the IJCAI-99 Workshop on Text Mining: Foundations, Techniques, and Applications. find
  16. Megumi Kameyama. 1997. Recognizing Referential Links: An Information Extraction Perspective. In Proceedings of the Workshop on Operational Factors in Practical, Robust Anaphora Resolution for Unrestricted Texts, (ACL-97/EACL-97), pages 46-53, Madrid, Spain. find
  17. Christopher Kennedy and Branimir Bogureav. 1996. Anaphora for everyone: Pronominal anaphora resolution without a parser. In Proceedings of the 16th International Conference on Computational Linguistics (COLING-96). find our card
  18. George A. Miller. 1995. WordNet: A Lexical Database. Communication of the A CM, 38(11):39-41. find
  19. Ruslan Mitkov. 1 9 9 8 . Robust pronoun resolution with limited knowledge. In Proceedings of COLING-ACL'98, pages 869-875. 1996. Proceedings of the Sixth Message Understanding Conference (MUC-6),Morgan Kaufmann, San Mateo, CA. 1998. Proceedings of the Seventh Message Understanding Conference (MUC-7)… find our card
  20. Philip Resnik and I. Dan Melamed. 1 9 9 7 . Semi-Automatic Acquisition of Domain-Specific Translation 1998. Lexicons. In Proceedings of the 5th ACL Conference on Applied Natural Language Processing (ANLP-97). find
  21. Ellen Riloff and Rosie Jones. 1999. Learning Dictionaries for Information Extraction by Multi-Level Bootstrapping. In Proceedings of the Sixteenth National Conference on Artificial Intelligence (AAAI-99). find
  22. Frank Smadja, Katheleen R. McKeown and Vasileios Hatzivassiloglou. 1996. Translating collocations for bilingual lexicons: A statistical approach. Computational Linguistics , 21(1):1-38. find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/harabagiu-2000-multilingual-coreference-resolution/