Are rule-based approaches a thing of the past? The case of anaphora resolution

  1. Mitkov, Ruslan
  2. Ha, Le An
Aldizkaria:
Procesamiento del lenguaje natural

ISSN: 1135-5948

Argitalpen urtea: 2024

Zenbakia: 73

Orrialdeak: 15-27

Mota: Artikulua

DIALNET GOOGLE SCHOLAR lock_openSarbide irekia editor

Beste argitalpen batzuk: Procesamiento del lenguaje natural

Laburpena

En este artículo evaluamos y comparamos nuevas variantes de un conocido algoritmo de resolución de anáforas basado en reglas con la versión original. Buscamos establecer si los enfoques que se benefician de aprendizaje profundo, grandes modelos de lenguaje (LLMs) y datos de eye-tracking (siempre) superan al algoritmo original basado en reglas. Los resultados de este estudio sugieren que, aunque los algoritmos basados en aprendizaje profundo y grandes modelos de lenguaje suelen rendir mejor que los basados en reglas, no siempre es así. Por lo tanto, sostenemos que los enfoques basados en reglas siguen teniendo cabida en la investigación actual.

Erreferentzia bibliografikoak

  • Baldwin, B. 1998. Coreference as the foundations for link analysis over free text databases. In Content Visualization and Intermedia Representations (CVIR’98).
  • Barrett, M., J. Bingel, F. Keller, and A. Søgaard. 2016. Weakly supervised part-of-speech tagging using eye-tracking data. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 579–584, Berlin, Germany, August. Association for Computational Linguistics.
  • Charniak, E. 2000. A maximum-entropy-inspired parser. In 1st Meeting of the North American Chapter of the Association for Computational Linguistics.
  • Clark, K. and C. D. Manning. 2015. Entity-centric coreference resolution with model stacking. In C. Zong and M. Strube, editors, Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 1405–1415, Beijing, China, July. Association for Computational Linguistics.
  • Clark, K. and C. D. Manning. 2016. Deep reinforcement learning for mention-ranking coreference models. In J. Su, K. Duh, and X. Carreras, editors, Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 2256–2262, Austin, Texas, November. Association for Computational Linguistics.
  • Colson, J.-P. 2019. Multi-word units in machine translation: why the tip of the iceberg remains problematic – and a tentative corpus-driven solution. In MUMTT2019, The 4th Workshop on Multi-word Units in Machine Translation and Translation Technology.
  • Cop, U., N. Dirix, D. Drieghe, and W. Duyck. 2016. Presenting GECO: An eyetracking corpus of monolingual and bilingual sentence reading. Behavior Research Methods, 49, 05.
  • Cunningham, H., D. Maynard, K. Bontcheva, V. Tablan, and Y. Wilks. 2000. Experience using GATE for NLP R&D. In R. Zajac, editor, Proceedings of the COLING-2000 Workshop on Using Toolsets and Architectures To Build NLP Systems, pages 1–8, Centre Universitaire, Luxembourg, August. International Committee on Computational Linguistics.
  • Duchowski, A. T. 2017. Eye Tracking Methodology: Theory and Practice. Springer Publishing Company, Incorporated, 3rd edition.
  • Evans, R. 2001. Applying machine learning toward an automatic classification of it. Literary and linguistic computing, 16(1):45–58.
  • Foraker, S. and B. McElree. 2007. The role of prominence in pronoun resolution: Active versus passive representations. Journal of Memory and Language, 56(3):357–383.
  • Ge, N., J. Hale, and E. Charniak. 1998. A statistical approach to anaphora resolution. In Sixth Workshop on Very Large Corpora.
  • Kennedy, A., R. Hill, and J. Pynte. 2003. The Dundee corpus. In Proceedings of the 12th European Conference on Eye Movement (ECEM-2003).
  • Lappin, S. and H. J. Leass. 1994. An algorithm for pronominal anaphora resolution. Computational Linguistics, 20(4):535–561.
  • Li, Y., P. Musilek, M. Reformat, and L. Wyard-Scott. 2009. Identification of pleonastic it using the web. J. Artif. Int. Res., 34(1):339–389, mar.
  • Liu, R., R. Mao, A. T. Luu, and E. Cambria. 2023. A brief survey on recent advances in coreference resolution. Artificial Intelligence Review.
  • Meng, Y. and A. Rumshisky. 2018. Triad-based neural network for coreference resolution. In E. M. Bender, L. Derczynski, and P. Isabelle, editors, Proceedings of the 27th International Conference on Computational Linguistics, pages 35–43, Santa Fe, New Mexico, USA, August. Association for Computational Linguistics.
  • Mitkov, R. 1996. Towards a more efficient use of PC-based MT in education. In Proceedings of Translating and the Computer 18, London, UK, November 14-15. Aslib.
  • Mitkov, R. 1998. Robust pronoun resolution with limited knowledge. In 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics, Volume 2, pages 869–875, Montreal, Quebec, Canada, August. Association for Computational Linguistics.
  • Mitkov, R. 2002. Anaphora Resolution. Longman.
  • Mitkov, R., editor. 2003. The Oxford Handbook of Computational Linguistics. Oxford University Press.
  • Mitkov, R. 2006. Fully automatic anaphora resolution for English and Bulgarian. In S. K. M. Slavcheva, M. and G. Angelova, editors, Readings in multilinguality. Institute for parallel processing, Bulgarian Academy of Sciences, pages 78–86.
  • Mitkov, R. 2019. Computer vs. human intelligence. Keynote speech at the Refinitiv conference, City of London.
  • Mitkov, R., editor. 2022. The Oxford Handbook of Computational Linguistics. Oxford University Press, 2nd substantially revised edition.
  • Mitkov, R. and C. Barbu. 2000. Mutual enhancement of performance: bilingual pronoun resolution for English and French. In DAARRC2000 - Discourse, Anaphora and Reference Resolution Conference.
  • Mitkov, R., L. Belguith, and M. Stys. 1998. Multilingual robust anaphora resolution. In N. Ide and A. Voutilainen, editors, Proceedings of the Third Conference on Empirical Methods for Natural Language Processing, pages 7–16, Palacio de Exposiciones y Congresos, Granada, Spain, June. Association for Computational Linguistics.
  • Mitkov, R. and L. H. Belguith. 1998. Robust pronoun resolution with limited knowledge: a high success rate approach for English and Arabic. In 6th Iberoamerican Conference on Artificial Intelligence (IBERAMIA’98).
  • Mitkov, R., R. Evans, and C. Orasan. 2002. A new, fully automatic version of mitkov’s knowledge-poor pronoun resolution method. In A. Gelbukh, editor, Computational Linguistics and Intelligent Text Processing, pages 168–186, Berlin, Heidelberg. Springer Berlin Heidelberg.
  • Mitkov, R. and M. Stys. 1997. Robust reference resolution with limited knowledge: high precision genre-specific approach for English and Polish. In Proceedings of the International Conference “Recent Advances in Natural Language Proceeding” (RANLP’97).
  • Nito´n, B., P. Morawiecki, and M. Ogrodniczuk. 2018. Deep neural networks for coreference resolution for Polish. In N. Calzolari, K. Choukri, C. Cieri, T. Declerck, S. Goggi, K. Hasida, H. Isahara, B. Maegaard, J. Mariani, H. Mazo, A. Moreno, J. Odijk, S. Piperidis, and T. Tokunaga, editors, Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), Miyazaki, Japan, May. European Language Resources Association (ELRA).
  • Orasan, C. and R. Evans. 2001. Learning to identify animate references. In Proceedings of the ACL 2001 Workshop on Computational Natural Language Learning (ConLL).
  • Peters, M., M. Neumann, M. Iyyer, M. Gardner, C. Clark, K. Lee, and L. Zettlemoyer. 2018. Deep contextualized word representations. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 2227–2237, New Orleans, Louisiana, June. Association for Computational Linguistics.
  • Plu, J., R. Prokofyev, A. Tonon, P. Cudré-Mauroux, D. E. Difallah, R. Troncy, and G. Rizzo. 2018. Sanaphor++: Combining deep neural networks with semantics for coreference resolution. In N. Calzolari, K. Choukri, C. Cieri, T. Declerck, S. Goggi, K. Hasida, H. Isahara, B. Maegaard, J. Mariani, H. Mazo, A. Moreno, J. Odijk, S. Piperidis, and T. Tokunaga, editors, Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), Miyazaki, Japan, May. European Language Resources Association (ELRA).
  • Rayner, K. 1998. Eye movements in reading and information processing: 20 years of research. Psychological bulletin, 124(3):372.
  • Rayner, K. and S. A. Duffy. 1986. Lexical complexity and fixation times in reading: Effects of word frequency, verb complexity, and lexical ambiguity. Memory & cognition, 14(3):191–201.
  • Rayner, K., A. Pollatsek, J. Ashby, and C. Clifton Jr. 2012. Psychology of reading.
  • Rohanian, O., S. Taslimipoor, V. Yaneva, and L. A. Ha. 2017. Using gaze data to predict multiword expressions. In Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017, pages 601–609, Varna, Bulgaria, September. INCOMA Ltd.
  • Rotsztejn, J. 2018. Learning from cognitive features to support natural language processing tasks. Master’s thesis, ETH Zurich.
  • Stuckardt, R. 2002. Machine-learning-based vs. manually designed approaches to anaphor resolution: the best of two worlds. In Proc.4th Discourse Anaphora and Anaphor Resolution Colloquium (DAARC2002).
  • Stuckardt, R. 2003. Coreference-based summarization and question answering: a case for high precision anaphor resolution. In Proc. 2003 Int. Symp. Reference Resolution and Its Application to QA and TS(ARQAS).
  • Stuckardt, R. 2005. A machine learning approach to preference strategies for anaphor resolution. In Anaphora Processing Linguistic, Cognitive and Computational Modeling edited by Branco, A., McEnery, A., Mitkov, R. John Benjamins, Amsterdam/Philadelphia.
  • Tanev, H. and R. Mitkov. 2002. Shallow language processing architecture for Bulgarian. In COLING 2002: The 19th International Conference on Computational Linguistics.
  • Tapanainen, P. and T. Jarvinen. 1997. A non-projective dependency parser. In Fifth Conference on Applied Natural Language Processing, pages 64–71, Washington, DC, USA, March. Association for Computational Linguistics.
  • Trinh, T. H. and Q. V. Le. 2018. A simple method for commonsense reasoning. CoRR, abs/1806.02847.
  • Vadász, N. 2023. Resolving Hungarian anaphora with ChatGPT. In K. Ekˇstein, F. Pártl, and M. Konopík, editors, Text, Speech, and Dialogue, pages 45–57, Cham. Springer Nature Switzerland.
  • Wiseman, S., A. M. Rush, and S. M. Shieber. 2016. Learning global features for coreference resolution. In K. Knight, A. Nenkova, and O. Rambow, editors, Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 994–1004, San Diego, California, June. Association for Computational Linguistics.
  • Yaneva, V., L. A. Ha, R. Evans, and R. Mitkov. 2018. Classifying referential and non-referential it using gaze. In E. Riloff, D. Chiang, J. Hockenmaier, and J. Tsujii, editors, Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 4896–4901, Brussels, Belgium, October-November. Association for Computational Linguistics.
  • Yang, X., E. Peynetti, V. Meerman, and C. Tanner. 2022. What GPT knows about who is who. In S. Tafreshi, J. Sedoc, A. Rogers, A. Drozd, A. Rumshisky, and A. Akula, editors, Proceedings of the Third Workshop on Insights from Negative Results in NLP, pages 75–81, Dublin, Ireland, May. Association for Computational Linguistics.
Datuen iturria: Dialnet