Robust Pronoun Resolution with Limited Knowledge
Summary
Classic anaphora resolution systems depend on rich syntactic, semantic and domain knowledge, which is expensive to build and slow to run. Mitkov proposes a lightweight alternative for resolving pronouns in technical manuals that needs only part-of-speech tagged text and simple noun-phrase rules, with no full parsing.
For each pronoun, the system:
- gathers noun phrases to its left within the current and two previous sentences,
- discards candidates that fail gender/number agreement, using a hand-built list of agreement exceptions,
- scores the remaining candidates with empirically chosen "antecedent indicators" such as definiteness, givenness, lexical reiteration, collocation patterns, referential distance and term status.
The highest total score wins, and fixed tie-breaking rules settle equal scores.
On English manuals the method resolved 89.7% of pronouns. This beat two baselines and a manually simulated CogNIAC. Ported to Polish and Arabic with small changes, it scored even higher. The work shows that cheap, preference-based heuristics can be robust and fairly portable across languages, at least within a restricted genre.
Key points
- Each indicator assigns a candidate a score of -1, 0, 1 or 2. Ties are broken by immediate reference, then collocation, then indicating verbs, and finally recency.
- English results: 89.7% success, versus 31.55%/48.55% (recall/precision) for a most-recent-subject baseline and 65.95% for a most-recent-NP baseline. CogNIAC ("resolve all", simulated manually) reached 75%.
- The most discriminative indicators were immediate reference (100%), non-prepositional NP (92.2%) and collocation (90.9%). The most frequently applied was referential distance (98.9% of anaphors).
- Polish adaptation: evaluated on 180 pronouns from online technical manuals, 120 of them exophoric. It reached 93.3% success (critical success rate 86.2%), compared with baselines of 23.7% and 68.4%.
- Arabic adaptation: 95.2% success (critical 89.3%) on 63 anaphors from a Sony technical manual.
Cited by
- Evaluation Tool for Rule-based Anaphora Resolution Methods
- A Generic Anaphora Resolution Engine for Indian Languages
- Multilingual Coreference Resolution
- A Coreference Corpus and Resolution System for Dutch
- Employing the Centering Theory in Pronoun Resolution from the Semantic Perspective
- Automatic Pronominal Anaphora Resolution in English Texts
- Pronominal and Sortal Anaphora Resolution for Biomedical Literature
- A Mention-Synchronous Coreference Resolution Algorithm Based On the Bell Tree
- Multi-Lingual Coreference Resolution With Syntactic Features
- Comparing Knowledge Sources for Nominal Anaphora Resolution
- Multigraph Clustering for Unsupervised Coreference Resolution
- Semantic Class Induction and Coreference Resolution
- An Algorithm for Anaphora Resolution in Spanish Texts
- Acquiring Lexical Knowledge for Anaphora Resolution
- Supervised Models for Coreference Resolution
- SemEval-2010 Task 1: Coreference Resolution in Multiple Languages
- A Corpus-Based Evaluation of Centering and Pronoun Resolution
- Identification des reprises et interprétation automatique des expressions pronominales dans des textes en français
- Coreference Resolution Using Competition Learning Approach
- Improving Pronoun Resolution by Incorporating Coreferential Information of Candidates
- Improving Pronoun Resolution Using Statistics-Based Semantic Compatibility Information
- Kernel-Based Pronoun Resolution with Structured Syntactic Knowledge
- UBIU: A Language-Independent System for Coreference Resolution
- A High-Performance Coreference Resolution System using a Constraint-based Multi-Agent Strategy
- Context-Sensitive Convolution Tree Kernel for Pronoun Resolution
Cite
@inproceedings{mitkov1998robust,
title = {{Robust Pronoun Resolution with Limited Knowledge}},
author = {Mitkov, Ruslan},
booktitle = {36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics, Volume 2},
year = {1998},
doi = {10.3115/980691.980712},
url = {https://doi.org/10.3115/980691.980712}
}References
- Baldwin, Breck. 1997. "CogNIAC: high precision coreference with limited knowledge and linguistic resources". Proceedings of the ACL'97/EACL'97 workshop on Operational factors in practical, robust anaphora resolution, 38-45, Madrid, Spain. find our card
- Brennan, S., M. Fridman and C. Pollard. 1987. A centering approach to pronouns. Proceedings of the 25th Annual Meeting of the ACL (ACL'87), 155-162, Stanford, CA, USA. find
- Carbonell, James G. & Ralf D. Brown. 1988. "Anaphora resolution: a multi-strategy approach". Proceedings of the 12. International Conference on Computational Linguistics (COLING'88), Vol.I. 96-101, Budapest, Hungary. find our card
- Carter, David M. 1987. Interpreting anaphora in natural language texts. find
- Chichester: Ellis Horwood Connoly, Dennis, John D. Burger & David S. Day. 1994. "A Machine learning approach to anaphoric reference". Proceedings of the International Conference "New Methods in Language Processing", 255-261, Manchester, United Kingdom. Dagan, ldo & Alon Itai. 1990. "Automatic proces… find
- Cambridge: Cambridge University Press Hobbs, Jerry R. 1978 "Resolving pronoun references". Lingua, 44, 339-352. find our card
- Ingria, Robert J.P. & David Stallard. 1989. "A computational mechanism for pronominal reference". Proceedings of the 27th Annual Meeting of the ACL, 262-271, Vancouver, British Columbia. find
- Internet Manual. 1994. Translation of Internet Manual lnternet i okolice: Przewodnik po swiatowych sieciach komputerowych. Tracy LaQuey, Jeanne C. Ryer Translated by Monika Zielinska, BIZNET Poland. find
- Java Manual. 1998. Jezyk Java. Clico, Krakow. find
- Kennedy, Christopher & Branimir Boguraev, 1996. "Anaphora for everyone: pronominal anaphora resolution without a parser". Proceedings of the 16th International Conference on Computational Linguistics (COLING'96), 113-118. find our card
- Copenhagen, Denmark Lappin, Shalom & Michael McCord. 1990. "Anaphora resolution in slot grammar". Computational Linguistics, 16:4, 197-212. find our card
- Lappin, Shalom & Herbert Leass. 1994. "An algorithm for pronominal anaphora resolution". Computational Linguistics, 20(4), 535-561. find our card
- Minolta. 1994. Minolta Operator's Manual for Photocopier EP5325. Technical Manual Minolta Camera Co., Ltd., Business Equipment Division 3-13, 2-Chome, Azuchi, -Machi, Chuo-Ku, Osaka 541, Japan Mitkov, Ruslan. 1994. "An integrated model for anaphora resolution". Proceedings of the 15th International… find our card
- Mitkov, Ruslan. 1995. "Un uncertainty reasoning approach for anaphora resolution". Proceedings of the Natural Language Processing Pacific Rim Symposium (NLPRS'95), 149-154, Seoul, Korea. find
- Mitkov, Ruslan. 1998a. "Pronoun resolution: the practical alternative". In T. McEnery, S. Botley(Eds) Discourse Anaphora and Anaphor Resolution. find
- John Benjamins. Mitkov, Ruslan. 1998b. "Evaluating anaphora resolution approaches". Proceedings of the Discourse Anaphora and Anaphora Resolution Colloquium (DAARC'2), (forthcoming) Lancaster, UK Mitkov, Ruslan & Malgorzata Stys. 1997. "Robust reference resolution with limited knowledge: high precis… find
- Mitkov, Ruslan & Lamia Belguith. 1998. "Pronoun resolution made simple: a robust, knowledge-poor approach in action". Proceedings of the International Conference "Traduction Automatique et Langage Naturel" (TALN'98) (forthcoming). find
- Paris, France. Rich, Elaine & Susann LuperFoy. 1988. "An architecture for anaphora resolution". Proceedings of the Second Conference on Applied Natural Language Processing (ANLP-2), 18-24, Texas, U.S.A. find our card
- Sidner, Candy L. 1979. Towards a computational theory of definite anaphora comprehension in English discourse. Technical Report No. 537. M.I.T., Artificial Intelligence Laboratory. find
- Sony. 1992. Video cassette recorder. Operating Instructions. Sony Corporation. find
- Stylewriter 1994. Portable StyleWriter. User's guide. Apple Computers. find
- Tin, Erkan & Varol, Akman. 1994. "Situated processing of pronominal anaphora". Proceedings of the KONVENS"94 Conference, 369-378, Webber, Bonnie L. 1979. A formal approach to discourse anaphora. London: Garland Publishing. find
- Williams, Sandra, Mark Harvey & Keith Preston. 1996. "Rule-based reference resolution for unrestricted text using part-of-speech tagging and noun phrase parsing". Proceedings of the International Colloquium on Discourse Anaphora and Anaphora Resolution (DAARC), 441-456. Lancaster, UK. find