Difficulties with computational coreference tracking: How to achieve ‘coherence in mind’ without a mind?
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
The introduction and maintenance of reference in discourse is subject to a number of language-universal constraints on NP form and selection that allow speakers to maintain reference co-referentially (i.e. from mention to mention) with minimal processing effort across large spans of discourse. Automated approaches to co-reference resolution (i.e. the successful tracking of discourse referents across texts) use a variety of models to account for how a referent may be tracked co-referentially, yet automated co-reference resolution is still considered an incredibly difficult task for those working in natural language processing and generation, even when using ‘gold-standard’ manually-annotated discourse texts as a source of comparison. Less research has been conducted on the performance of automated co-reference resolution on narrative data, which is rich with multiple referents interacting with each other, with long sequences of continuous and non-continuous reference to be maintained. Five freely-available co-reference resolvers were trialled for accuracy on oral narrative data produced by English native speakers using a picture sequence as an elicitation device. However, accuracy levels of under 50% for each resolver tested suggest large differences between human and computational methods of co-reference resolution. In particular, zero anaphora, NPs with modifiers and errors in coding first-mentioned referents appear particularly problematic. This suggests that automated approaches to coreference resolution need a vast range of lexical knowledge, inferential capabilities based on situational and world knowledge, and the ability to track reference over extended discourse if they are to succeed in modelling human-like coreference resolution.
Abstract
The introduction and maintenance of reference in discourse is subject to a number of language-universal constraints on NP form and selection that allow speakers to maintain reference co-referentially (i.e. from mention to mention) with minimal processing effort across large spans of discourse. Automated approaches to co-reference resolution (i.e. the successful tracking of discourse referents across texts) use a variety of models to account for how a referent may be tracked co-referentially, yet automated co-reference resolution is still considered an incredibly difficult task for those working in natural language processing and generation, even when using ‘gold-standard’ manually-annotated discourse texts as a source of comparison. Less research has been conducted on the performance of automated co-reference resolution on narrative data, which is rich with multiple referents interacting with each other, with long sequences of continuous and non-continuous reference to be maintained. Five freely-available co-reference resolvers were trialled for accuracy on oral narrative data produced by English native speakers using a picture sequence as an elicitation device. However, accuracy levels of under 50% for each resolver tested suggest large differences between human and computational methods of co-reference resolution. In particular, zero anaphora, NPs with modifiers and errors in coding first-mentioned referents appear particularly problematic. This suggests that automated approaches to coreference resolution need a vast range of lexical knowledge, inferential capabilities based on situational and world knowledge, and the ability to track reference over extended discourse if they are to succeed in modelling human-like coreference resolution.
참고문헌 (46)
- Ariel, Mira, "The function of accessibility in a theory of grammar", Journal of Pragmatics, 16(5), pp.443~463 (1991)
- Ariel, Mira., "Reference and referent accessibility" (1996), John Benjamins
- Ariel, Mira, "Pragmatics and grammar" (2008), Cambridge University Press
- Ariel, Mira, "Defining pragmatics" (2010), Cambridge University Press
- "The OpenNLP Project" (2005)[URL]
- Brennan, Susan, "A centering approach to pronouns", Proceedings of the 25th Annual Meeting on Association for Computational Linguistics, pp.155~162 (1987)
- Cai, Jie Eva Mujdricza-Maydt, "Unrestricted coreference resolution via global hypergraph partitioning", Proceedings of the Fifteenth Conference on Computational Natural Language Learning: Shared task, pp.56~60 (2011)
- Charniak, Eugene, "A maximum-entropy-inspired parser", Proceedings of the 1st North American Chapter of the Association for Computational Linguistics Conference, pp.132~139 (2000)
- Charniak, Eugene, "Coarse-to-fine n-best parsing and MaxEnt discriminative reranking", Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics, pp.173~180 (2005)
- Choi, Miji, "Evaluation of coreference resolution for biomedical text", Proceedings of the SIGIR Workshop on Medical Information Retrieval (MEDIR 2014) (2014)
- Clark, Eve, "The handbook of language emergence" (2015), Wiley
- Crosthwaite, Peter, "Differences between the coherence of Mandarin and Korean L2English learner production and English native speakers: An empirical study", 박사, pp.2014
- Doddington, George, "The automatic content extraction (ACE) program—tasks, data, and evaluation", Proceedings of the 4th conference on language resources and evaluation (LREC 2004), pp.837~840 (2004)
- Finkel, Jenny, "Enforcing transitivity in coreference resolution", Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics (ACL-HLT 2008), pp.45~48 (2008)
- Gernsbacher, Morton Ann, "Coherence in spontaneous text" (1995), John Benjamins
- Givón, Talmy, "Coherence in spontaneous text", pp.59~115 (1995), John Benjamins
- Grice, Herbert Paul, "Syntax and Semantics 3", pp.41~58 (1975), Academic Press
- Grosz, Barbara. J., "Attention, intentions, and the structure of discourse", Computational Linguistics, 12(3), pp.175~204 (1986)
- Grosz, Barbara. J., "Centering: A framework for modeling the local coherence of discourse", Computational Linguistics, 21(2), pp.203~225 (1995)
- Gundel, Jeanette. K., "Cognitive status and the form of referring expressions in discourse", Language, 69(2), pp.274~307 (1993)
- Haghighi, Aria, "Simple coreference resolution with rich syntactic and semantic features", Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, 3, pp.1152~1161 (2009)
- Halliday, Michael, "Cohesion in English" (1976), Longman
- Hasan, Ruqaiya, "Understanding reading comprehension", pp.181~219 (1984), International Reading Association
- Hawkins, John, "Efficiency and complexity in grammars" (2004), Oxford University Press
- Hirschman, Lynette, "MUC-7 coreference task definition—version 3.0", Proceedings of the 7th Message Understanding Conference (MUC-7) (1997)
- Klein, Dan, "Advances in neural information processing systems", pp.3~10 (2003)
- Kudoh, Taku, "Use of support vector learning for chunk identification", Proceedings of the 2nd Workshop on Learning Language in Logic and the 4th Conference on Computational Natural Language Learning, 7, pp.142~144 (2000)
- Lappin, Shalom, "An algorithm for pronominal anaphora resolution", Computational Linguistics, 20(4), pp.535~561 (1994)
- Lee, Heeyoung, "Deterministic coreference resolution based on entity-centric, precision-ranked rules", Computational linguistics, 39(4), pp.885~916 (2013)
- Levinson, Steven C, "Roots of human sociality: Culture, cognition, and interaction", pp.39~69 (2006), Berg
- Luo, Xiaoqiang, "On coreference resolution performance metrics", Proceedings of the Joint Conference on Human Language Technology and Empirical Methods in Natural Language Processing (HLT-EMNLP 2005), pp.37~48 (2005)
- Marquez, Lluis, "Coreference resolution: An empirical study based on SemEval-2010 Shared Task 1", Language resources and evaluation, 47, pp.661~694 (2013)
- Mitkov, Ruslan, "A new, fully automatic version of Mitkov’s knowledge-poor pronoun resolution method", Computational linguistics and intelligent text processing, pp.69~83 (2010)
- Orasan, Constantin, "Anaphora resolution exercise: An overview", Proceedings of the 6th Conference on Language Resources and Evaluation (LREC 2008), pp.28~30 (2008)
- Qiu, Long, "A public reference implementation of the RAP anaphora resolution algorithm", Proceedings of the Language Resources and Evaluation Conference, pp.291~294 (2004)
- Rahman, Altaf, "Coreference resolution with world knowledge", Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics:Human Language Technologies, 1, pp.814~824 (2011), Association for Computational Linguistics
- Recasens, Marta, "Coreference: Theory, annotation, resolution and evaluation", Ph.D, pp.2010
- Sapena, Emili, "Relaxcor: A global relaxation labeling approach to coreference resolution", Proceedings of the Association for Computational Linguistics (ACL) Workshop on Semantic Evaluations (SemEval- 2010), pp.88~91 (2010)
- "The edmonton narrative norms instrument" (2003)[URL]
- Sperber, Dan, "Relevance: Communication and cognition" (1995), Blackwell
- Stalnaker, Robert, "Semantics and philosophy: Essays", pp.197~213 (1974), New York University Press
- Stoyanov, Vaselin, "Coreference resolution with Reconcile", Proceedings of the Association for Computational Linguistics (ACL) 2010 conference short papers, pp.156~161 (2010)
- Tapanainen, Pasi, "A non-projective dependency parser", Proceedings of the fifth conference on applied natural language processing, pp.64~71 (1997)
- Toutanova, Kristina, "Feature-rich part-of-speech tagging with a cyclic dependency network", Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology, 1, pp.173~180 (2003)
- Versley, Yannick, "BART: A modular toolkit for coreference resolution", Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics on Human Language Technologies: Demo session, pp.9~12 (2008)
- Zhou, Guodong, "A high-performance coreference resolution system using a constraint-based multi-agent strategy", Proceedings of the 20th International Conference on Computational Linguistics (COLING 2012), pp.522~528 (2004), Association for computational linguistics