Multilingual Robust Anaphora Resolution
Summary
Pronoun resolution systems of the 1990s usually depended on rich syntactic, semantic and domain knowledge, which is costly to build and nearly always targeted English only. This paper adapts the authors' earlier practical approach (Mitkov 1998a) into a lightweight, parser-free method for pronouns in technical manuals and tests it in three languages: English, Polish and Arabic. The text is first split into sentences, POS-tagged and chunked into noun phrases. Candidate antecedents from the current and two preceding sentences must pass a gender and number agreement check. Each surviving candidate is then scored by a set of empirically derived "antecedent indicators," such as definiteness, givenness, indicating verbs, term preference and referential distance. The highest total score determines the antecedent, and fixed tie-breaking rules handle equal scores. Adapting the method to Polish and Arabic took only small, language-specific changes, and the unmodified version already performed reasonably well. Success rates reached about 90% or higher, which suggests that cheap, knowledge-poor methods can serve as a practical multilingual baseline, including for morphologically rich languages.
Key points
- English achieved an overall success rate of 89.7%, while Polish and Arabic reached 93.3% and 95.2% respectively. The English evaluation was the most extensive.
- For Arabic, the unadapted ("Arabic direct") version resolved 57 of 63 anaphors (90.5%), and the adapted version ("Arabic improved") resolved 60 of 63. The adapted version changed the non-prepositional phrase and referential distance indicators, and its critical success rate rose from 78.6% to 89.3%.
- The Polish test set came from online technical manuals and contained 180 pronouns, 120 of them exophoric (mostly zero pronouns). The unmodified version scored 90%, and the critical success rate was 86.2%.
- The two Polish baselines performed far worse: "Baseline Subject" reached 23.7% and "Baseline Most Recent" reached 68.4%.
- Each indicator scores a candidate between −1 and 2. The most discriminative indicators (immediate reference, sequential instructions, collocation) were also among the least frequently triggered.
Cited by
- Creating a Coreference Resolution System for Polish
- Creating a Coreference Resolution System for Italian
- A Probabilistic Method for Analyzing Japanese Anaphora Integrating Zero Pronoun Detection and Resolution
Cite
@inproceedings{mitkov1998multilingual,
title = {{Multilingual Robust Anaphora Resolution}},
author = {Mitkov, Ruslan and Belguith, Lamia and Stys, Malgorzata},
booktitle = {Proceedings of the Third Conference on Empirical Methods for Natural Language Processing},
year = {1998},
url = {https://aclanthology.org/W98-1502/}
}References
- Abra,os, Jose & Jose G. Lopes. 1994. "Extending DRT with a focusing mechanism for pronominal anaphora and ellipsis resolution". Proceedings of the 15th International Conference on Complt!ational Linguistics (COL/NG'94), 1128-1132, Kyoto, Japan. find
- Baldwin, Breck. 1997. "CogNIAC: high precision corefer-encc with limited knowledge and linguistic resources". Proceedings of the ACL'97/EACL'97 workshop on Operational factors in practical, robust arzaphora resolution, 38-45, Madrid, Spain. find
- 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.!, 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". find
- Proceedings of the International Conference "New Methods in Language Processing", 255-261, Manchester, United Kingdom. Dagan, Ida & Alan ltai. 1990. "Automatic processing of large corpora for the resolution of anaphora references". find our card
- Proceedings of the 13thelnternational Conference on ComputationaL Linguistics (COLING'90), Vol. III, I-3, Helsinki, Finland. find
- Dagan, Ida, John Justeson, Shalom Lappin, Herbert Leass & Amnon Ribak. 1995. Syntax and lexical statistics in anaphora resolution. Applied Artificial Intelligence, 9. find
- Dunker, Guido & Carla Umbach. 1993. Ve1jahren zur Anaphernresolll!ion in KIT-fAST. Internal Report KIT~ 28, Technical University of Berlin. find
- Firbas, Jan. 1992. Functional sentence perspective in written and spoken communication. Cambridge: Cambridge University Press. find
- Fischer, Ingrid, Bernd Gcistert & GUnter GOrz 1996. "Incremental anaphora resolution in a chart-based semantics construction framework using 1-DRT". Proceedings of the International Colloquium on Discourse Anaphora and Anaphora Resolution. Lancaster (DAARC), 235-244, Lancaster, UK. find
- Fraurud, Kari. 1988. "Pronoun Resolution in unrestricted text". Nordic Journal of Linguistics II, 47-68 find
- Galaini, Chikh Mustafa. 1992. Jami'u al-durus al-arabiah (Arabic lessons collection). Beirut: Manshurat al-maktabah al-asriyah (Modern library). find
- Hasan, Abbes. 1975. Al-nahw al-wafi ma'a rabtihi bi-al-asalib al-rafiah wa al-hayah al-loghawiah al-mutajadidah (Complete grammar referring to good styles and the changing language). Egypt: Dar al-ma'arif (Knowledge bookstore). find
- 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 Internet i okolice: Przewodnik po swiatowych sieciach komputerowych. Tracy LaQuey, Jeanne C. Ryer Translated by Monika Zielinska, BIZNET Poland. find
- Java Manual. 1998. Jezyk Java. find
- Clico, Krakow. Kennedy, Christopher & Branimir Boguraev, 1996. "Anaphora for everyone: pronominal anaphora resolution without a parser". Proceedings of the 16th Intemational Conference on Computational Linguistics (COL!NG'96), 1 13Hl18. find our card
- Copenhagen, Denmark. Lappin, Shalom & Michael McCord. 1990. "Anaphora resolution in slot grammar". Computationd Linguistics, 16:4, 197-212. find our card
- Lappin, Shalom & Herbert Leass. 1994. "11-n algorithm for pronominal anaphora resolution". Computational Linguistics, 20(4), 535-56!. find
- Leass Herbert & Ulrike Schwall. 1991. An anaphora resolution procedure for machine translation. IBM Germany Science Center. Institute for Knowledge Based Systems, Report 172. find
- 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. find
- Mitkov, Ruslan. 1994. "An integrated model for anaphora resolution". Proceedings of the 15th International Conference on Computational Linguistics (COL!NG'94), 1170-1176, Kyoto, Japan. find our card
- Mitkov, H.uslan. 1995. "Un uncertainty reasoning approach for anaphora resolution". Proceedings of the Natural Language Processing Pacific Rim Symposium (NLPRS'95), 149-154, Seoul, Korea. Mitkov, Ruslan. I998a. "Pronoun resolution: the practicai alternative". In T. McEnery, S. Botlcy(Eds) Discourse… find
- Mitkov, Ruslan. 1998b. "Evaluating anaphora resolution approaches" (forthcoming). find
- Mitkov, Ruslan & Malgorzata Stys. 1997. "Robust reference resolution with limited knowledge: high precision genre-specific approach for English and Polish". Proceedings of the international Conference "Recent Advances in Natural Language Proceeding" (RANLP'97), 74-8!. Tzigov Chark, Bulgaria. find
- Mori, Tatsunori, Mamoru Matsuo, Hiroshi Nakagawa. 1997. Constraints and defaults of zero pronouns in Japanese instruction manuals. Proceedings of the ACL'97/EACL'97 workshop on Operational factors in practical, robust anaphora resolution, 7-13. find
- Madrid, Spain. Nakaiwa, Hiromi & Satoru, Ikehara. 1992. " Zero pronoun resolution in a Japanese-to-English Machine Translation system by using verbal semantic attributes". Proceedings of 3rd Conference on Applied Natural Language Processing (ANLP'92), Trento, Italy. find
- Nakaiwa, Hiromi & Satoru, Ikehara. 1995. "lntrasentential resolution of Japanese zero pronouns in a Machine Translation system using semantic and pragmatic constraints". Proceeedings of the International Conference on Theoretical and Merhodological Issues in Machine Translation (TM!'95), 96-105, Leu… find
- Nakaiwa, Hiromi, S. Shirai, Satoru Ikehara & T. Kawaoka. 1995. "Extrasentential resolution of Japanese zero pronouns using semantic and pragmatic constraints". Proceedings of the AAAI I995 Spring Symposium Series: Empirical methods in discourse intetpretation and generation. find
- Nakaiwa, Hiromi & Francis Bond, Takahiro Uekado & Yayoi Nozawa. 1996. "Resolving zero pronouns in texts using textual structure". Proceedings of the International Conference "New Methods in Language Processing" (NeMLaP-2), Ankara, Turkey. find
- Nasukawa, Tetsuya. 1994. "Robust method of pronoun resolution using full-text information". Proceedings of the 15th International Conference on Computational ,Linguistics (COLJNG'94), 1157-1163, Kyoto, Japan. find our card
- Pomerol, Jean-Charles & Sergio Barbara-Romero. 1992. Choix multicritere dans l'entreprise: principes et pratique. find
- Paris: HERMES. Popescu-Belis, Andrei & Isabelle Robba. 1997. "Cooperation between pronoun and reference resolution for unrestricted texts". Proceedings of rhe ACL'97/EACL'97 workshop on Operational factors in practical, robust anaphora resolution, 30-37. find
- Madrid, Spain. 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
- Rolbert, Moniquc. 1989. Resolution de formes pronominales dans l'intetjace d'interogation d'une base de donnees. ThCse de doctorat. Facult6 des sciences de Luminy. find
- Sidner, Candy L. 1979. Towards a computational themy of definite anaphora comprehension in English discourse. Technical Report No. 537. find
- M.I.T., Artificial Intelligence Laboratory. Sony. 1992. Video cassette recorder. find
- Operating Instructions. Sony Corporation. Stuckardt, Roland. 1996. "An interdependency-sensitive approach to anaphor resolution". Proceedings of the International Colloquium on Discourse Anaphora and Anaphora Resolution. Lancaster (DMRC), 400AI3. Lancaster, UK. find
- Stuckardt, Roland. 1997. "Resolving anaphoric references on deficient syntactic descriptions". Proceedings of the ACL'97!EAC~'97 workshop on Operational factors in practical, robust anaphora resolution, 30fi37. Madrid, Spain. find
- Stylewriter 1994. Portable Style Writer. User's guide. Apple Computers. find
- Tin, Erkan & Varol, Akman. 1994. "Situated processing of pronominal anaphora". Proceedings of the KONVENS"94 Conference, 369fi378, Vienna, Austria. find
- Wakao, Takahiro. 1994. "Reference resolution using semantic patterns in Japanese newspaper articles". Proceedings of the 15th International Conference on Computational Linguistics (COLJNG'94), 1133-1137. Kyoto, Japan. find
- 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 Dis· course Anaphora and Anaphora Resolution (DAARC), 441-456. Lancaster, UK. find
This page in Markdown → https://md.research.elamur.ai/free/papers/mitkov-1998-multilingual-robust-anaphora-resolution/