Elamur Research⌕
☰
home / papers / 2019 / A Neural Entity Coreference Resolution Review

A Neural Entity Coreference Resolution Review

Paper · 2019 · Nikolaos Stylianou and Ioannis Vlahavas

Summary

This survey maps how neural networks have been applied to Entity Coreference Resolution, which links every expression in a document that points to the same real-world entity. The authors selected 152 publications using a PRISMA-style procedure. They searched publishers, Google Scholar and Arxiv, followed citation chains, and then filtered the results for quality and relevance. They first set out the linguistic groundwork: the kinds of English anaphora, the syntactic and semantic constraints on linking, and how coreference differs from anaphora resolution. They then review datasets and metrics. Neural systems are sorted into Mention-Pair, Mention-Ranking, Entity-Based, Latent-Structure and Language-Modelling families, and Pronoun Resolution (including gender bias) gets its own section. The main conclusions are critical:

  • CoNLL 2012 can no longer serve as the only benchmark.
  • Current metrics have flaws that are not fixed by averaging them together.
  • Systems use too much memory and computation to be easily combined with other tasks.

The paper recommends concrete metrics, annotation practices and cheaper ways to build data, so it works as a roadmap toward shared standards in the field.

Key points

  • The corpus of reviewed work has 152 items, made up of 105 papers from conferences, 22 articles from journals, 19 preprints and 6 books.
  • CoNLL 2012 has several weaknesses:
    • singletons are not labelled;
    • the train, development and test splits overlap heavily;
    • it carries gender bias;
    • few pronoun cases need more than number and gender cues, which inflates apparent progress.
  • LitBank is starting to be used as a cross-domain benchmark, but the authors do not see it as a replacement for CoNLL 2012.
  • Recommended metrics:
    • for unrestricted coreference, combine LEA (as a substitute for MUC), NEC (which rewards correct handling of named entities) and CEAF, with an averaged F1 in the CoNLL style;
    • for Pronoun Resolution, add Consistency.
  • Recommended resource building:
    • the Prange et al. (2019) annotation scheme and the Aralikatte and Søgaard (2020) annotation methodology;
    • Bornstein et al. (2020) crowdsourcing tooling;
    • Li et al. (2020) active learning, which limits annotation to the hard decisions.

Interesting ideas

  • I1. The survey lists anaphoric types, each with its own behaviour: zero, one, pronominal, demonstrative (proximal vs distal), presupposition, split antecedents, bridging, generics, non-referential and cataphora. Reporting results per type shows which phenomena a resolver actually handles.
  • I2. Detecting non-referential "it" (pleonastic uses, clefts, extrapositions) is treated as a required step before searching for an antecedent, which prevents spurious links.
  • I3. Syntactic and semantic constraints should prune the candidate referents before any scoring happens. This makes each linking decision traceable to the rule that allowed or blocked it.
  • I4. A benchmark that pronoun cues alone can solve creates a false sense of progress. Evaluation should deliberately include cases that need world knowledge and should check that decisions stay consistent.
  • I5. Active learning that sends only the hard coreference decisions to annotators cuts labelling cost while keeping the data useful for training.

For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

  • I1 (frames): The coreference module could tag every link with its anaphora type and report accuracy per type, so that gaps such as split antecedents or bridging become visible and explainable.
  • I2 (frames): A rule-based filter over the UD tree (for example expletive relations and extraposition patterns) could mark such pronouns before frame building, so no fake entity enters the world.
  • I3 (frames): Agreement and binding checks could run as explicit filters over UD-derived mentions, with each rejection logged as part of the explanation trail.
  • I4 (learn): A negative-control set could keep gender and number cues identical, so only world knowledge can separate the candidates, and a consistency check could catch contradictory resolutions.
  • I5 (learn): Witness parsers or resolvers could vote, and only the links they disagree on would go to the expensive LLM teacher tier.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

Also on the byline: Aristotle University of Thessaloniki.

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 9,086 worksArtificial Intelligence · 8,889 worksArts and Humanities · 9,296 worksLanguage and Linguistics · 9,206 worksComputer Vision and Pattern Recognition · 1,282 works

🧭 Topics 1Research subjects and languages the work is about.Coreference resolution · 550 works

Cite

Cite as Nikolaos Stylianou and Ioannis Vlahavas. 2019. A Neural Entity Coreference Resolution Review. Expert Systems with Applications, Volume 168, 15 April 2021, 114,466.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.1016/j.eswa.2020.114466 · arXiv 1910.09329

@inproceedings{stylianou2019neural,
  title = {{A Neural Entity Coreference Resolution Review}},
  author = {Nikolaos Stylianou and Ioannis Vlahavas},
  booktitle = {Expert Systems with Applications, Volume 168, 15 April 2021, 114466},
  year = {2019},
  doi = {10.1016/j.eswa.2020.114466},
  eprint = {1910.09329},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.1016/j.eswa.2020.114466}
}

References

155 references, 84 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Agarwal, O., Subramanian, S., Nenkova, A., Roth, D., 2019. Evaluation of named entity coreference, in: Proceedings of the Second Workshop on Computational Models of Reference, Anaphora and Coreference, Association for Computational Linguistics, Minneapolis, USA. pp. 1–7. URL: https://www.aclweb.org/anthology/W19-2801. ↗
  2. Al-Rfou’, R., Perozzi, B., Skiena, S., 2013. Polyglot: Distributed word representations for multilingual NLP, in: Proceedings of the Seventeenth Conference on Computational Natural Language Learning, Association for Computational Linguistics, Sofia, Bulgaria. pp. 183–192. URL: https://www.aclweb.org/anthology/W13-3520. ↗
  3. Aralikatte, R., Lent, H., Gonzalez, A.V., Herschcovich, D., Qiu, C., Sandholm, A., Ringaard, M., Søgaard, A., 2019. Rewarding coreference resolvers for being consistent with world knowledge, in: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Association for Computational Linguistics, Hong Kong, China. pp. 1229–1235. URL: https://www.aclweb.org/anthology/D19-1118, doi:10. 18653/v1/D19-1118. ↗
  4. Aralikatte, R., Søgaard, A., 2020. Model-based annotation of coreference, in: Proceedings of the 12th Language Resources and Evaluation Conference, European Language Resources Association, Marseille, France. pp. 74–79. URL: https://www.aclweb.org/anthology/2020.lrec-1.9. ↗
  5. de Arruda, H.F., Costa, L.d.F., Amancio, D.R., 2016. Using complex networks for text classification: Discriminating informative and imaginative documents. EPL (Europhysics Letters) 113, 28007. ↗
  6. Attree, S., 2019. Gendered ambiguous pronouns shared task: Boosting model confidence by evidence pooling, in: Proceedings of the First Workshop on Gender Bias in Natural Language Processing, Association for Computational Linguistics, Florence, Italy. pp. 134–146. URL: https://www.aclweb.org/anthology/W19-3820, doi:10.18653/v1/W19-3820. ↗
  7. Bagga, A., Baldwin, B., 1998. Algorithms for scoring coreference chains, in: The first international conference on language resources and evaluation workshop on linguistics coreference, Granada. pp. 563–566.
  8. Bahdanau, D., Cho, K., Bengio, Y., 2014. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 . ↗
  9. Bamman, D., Lewke, O., Mansoor, A., 2020. An annotated dataset of coreference in english literature, in: LREC. ↗
  10. Barros, C., Lloret, E., Saquete, E., Navarro-Colorado, B., 2019. Natsum: Narrative abstractive summarization through cross-document timeline generation. Information Processing & Management 56, 1775–1793. ↗
  11. Bengtson, E., Roth, D., 2008. Understanding the value of features for coreference resolution, in: Proceedings of the Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics. pp. 294–303.
  12. Bhattacharjee, S., Haque, R., de Buy Wenniger, G.M., Way, A., 2020. Investigating query expansion and coreference resolution in question answering on bert, in: International Conference on Applications of Natural Language to Information Systems, Springer. pp. 47–59. find
  13. Biber, D., Conrad, S., 2019. Register, genre, and style. Cambridge University Press. ↗
  14. Björkelund, A., Kuhn, J., 2014. Learning structured perceptrons for coreference resolution with latent antecedents and non-local features, in: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 47–57.
  15. Bornstein, A., Cattan, A., Dagan, I., 2020. Corefi: A crowd sourcing suite for coreference annotation. arXiv preprint arXiv:2010.02588 . ↗
  16. Cai, J., Strube, M., 2010. Evaluation metrics for end-to-end coreference resolution systems, in: Proceedings of the SIGDIAL 2010 Conference, Association for Computational Linguistics, Tokyo, Japan. pp. 28–36. URL: http://www.aclweb.org/anthology/W10-4305. ↗
  17. Cao, Y.T., Daumé III, H., 2020. Toward gender-inclusive coreference resolution, in: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics, Online. pp. 4568–4595. URL: https://www.aclweb.org/anthology/2020.acl-main.418, doi:10.18653/v1/2020.acl-main.418. ↗
  18. Caramazza, A., Grober, E., Garvey, C., Yates, J., 1977. Comprehension of anaphoric pronouns. Journal of Verbal Learning and Verbal Behavior 16, 601 – 609. URL: http://www.sciencedirect.com/science/article/pii/S0022537177800224, doi:https://doi.org/10.1016/S0022-5371(77) 80022-4. ↗
  19. Chang, K.W., He, H., Daumé III, H., Langford, J., 2015. Learning to search for dependencies. arXiv preprint arXiv:1503.05615 . ↗
  20. Chang, K.W., Samdani, R., Roth, D., 2013. A constrained latent variable model for coreference resolution, in: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics, Seattle, Washington, USA. pp. 601–612. URL: https://www.aclweb.org/anthology/D13-1057. ↗
  21. Charton, E., Gagnon, M., 2011. Poly-co: a multilayer perceptron approach for coreference detection, in: Proceedings of the Fifteenth Conference on Computational Natural Language Learning: Shared Task, Association for Computational Linguistics. pp. 97–101.
  22. Chen, C., Ng, V., 2013. Linguistically aware coreference evaluation metrics, in: Proceedings of the Sixth International Joint Conference on Natural Language Processing, pp. 1366–1374.
  23. Chen, H., Fan, Z., Lu, H., Yuille, A., Rong, S., 2018. PreCo: A large-scale dataset in preschool vocabulary for coreference resolution, in: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics, Brussels, Belgium. pp. 172–181. URL: https://www.aclweb.org/anthology/D18-1016, doi:10.18653/v1/D18-1016. ↗
  24. Chen, J., Lin, S.t., Durrett, G., 2019. Multi-hop question answering via reasoning chains. arXiv preprint arXiv:1910.02610 . ↗
  25. Chen, Y.H., Choi, J.D., 2016. Character identification on multiparty conversation: Identifying mentions of characters in tv shows, in: Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue, Association for Computational Linguistics. pp. 90–100. URL: http://aclweb.org/anthology/W16-3612, doi:10.18653/v1/W16-3612. ↗
  26. Chinchor, N., 1998. Overview of muc-7, in: Seventh Message Understanding Conference (MUC-7): Proceedings of a Conference Held in Fairfax, Virginia, April 29-May 1, 1998. find
  27. Chomsky, N., 1981. Lectures on government and binding. Foris, Dordrecht. . find
  28. Clark, K., Khandelwal, U., Levy, O., Manning, C.D., 2019. What does BERT look at? an analysis of BERT’s attention, in: Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, Association for Computational Linguistics, Florence, Italy. pp. 276– 286. URL: https://www.aclweb.org/anthology/W19-4828, doi:10.18653/ v1/W19-4828. ↗
  29. Clark, K., Manning, C.D., 2015. Entity-centric coreference resolution with model stacking, in: 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), Association for Computational Linguistics, Beijing, China. pp. 1405–1415. URL: https://www.aclweb.org/anthology/P15-1136, doi:10.3115/v1/P15-1136. ↗
  30. Clark, K., Manning, C.D., 2016a. Deep reinforcement learning for mention-ranking coreference models, in: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics, Austin, Texas. pp. 2256–2262. URL: https://www.aclweb.org/anthology/D16-1245, doi:10.18653/v1/D16-1245. ↗
  31. Clark, K., Manning, C.D., 2016b. Improving coreference resolution by learning entity-level distributed representations, in: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Association for Computational Linguistics, Berlin, Germany. pp. 643–653. URL: https://www.aclweb.org/anthology/P16-1061, doi:10.18653/v1/P16-1061. ↗
  32. Correa Jr, E.A., Lopes, A.A., Amancio, D.R., 2018. Word sense disambiguation: A complex network approach. Information Sciences 442, 103–113. ↗
  33. Cybulska, A., Vossen, P., 2014. Guidelines for ECB+ annotation of events and their coreference. Technical Report. Technical Report NWR-2014-1, VU University Amsterdam. find
  34. Dai, Z., Fei, H., Li, P., 2019. Coreference aware representation learning for neural named entity recognition., in: IJCAI, pp. 4946–4953. find
  35. van Deemter, K., Kibble, R., 2000. On coreferring: Coreference in muc and related annotation schemes. Computational Linguistics 26, 629–637. doi:10. 1162/089120100750105966. ↗
  36. Denis, P., Baldridge, J., 2007. Joint determination of anaphoricity and coreference resolution using integer programming, in: Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Proceedings of the Main Conference, pp. 236– 243.
  37. Devlin, J., Chang, M., Lee, K., Toutanova, K., 2018. BERT: pre-training of deep bidirectional transformers for language understanding. CoRR abs/1810.04805. URL: http://arxiv.org/abs/1810.04805, arXiv:1810.04805. ↗
  38. Doddington, G., Mitchell, A., Przybocki, M., Ramshaw, L., Strassel, S., Weischedel, R., 2004. The automatic content extraction (ace) program – tasks, data, and evaluation, in: Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC’04), European Language Resources Association (ELRA). URL: http://www.lrec-conf.org/proceedings/lrec2004/pdf/5.pdf. ↗
  39. Durrett, G., Klein, D., 2013. Easy victories and uphill battles in coreference resolution, in: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pp. 1971–1982.
  40. Emami, A., Trichelair, P., Trischler, A., Suleman, K., Schulz, H., Cheung, J.C.K., 2019. The KnowRef coreference corpus: Removing gender and number cues for difficult pronominal anaphora resolution, in: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics, Florence, Italy. pp. 3952–3961. URL: https://www.aclweb.org/anthology/P19-1386, doi:10.18653/v1/P19-1386. ↗
  41. Fellbaum, C., 1998. A semantic network of english: the mother of all wordnets, in: EuroWordNet: A multilingual database with lexical semantic networks. Springer, pp. 137–148. find
  42. Fernandes, E.R., Dos Santos, C.N., Milidiú, R.L., 2012. Latent structure perceptron with feature induction for unrestricted coreference resolution, in: Joint Conference on EMNLP and CoNLL-Shared Task, Association for Computational Linguistics. pp. 41–48.
  43. Ghaddar, A., Langlais, P., 2016. Wikicoref: An english coreference-annotated corpus of wikipedia articles., in: LREC.
  44. Grishman, R., Sundheim, B., 1996. Message understanding conference-6: A brief history, in: COLING 1996 Volume 1: The 16th International Conference on Computational Linguistics. find
  45. Gu, J.C., Ling, Z.H., Indurkhya, N., 2018. A study on improving end-to-end neural coreference resolution, in: Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data. Springer, pp. 159–169.
  46. Guillou, L., Hardmeier, C., Smith, A., Tiedemann, J., Webber, B., 2014. ParCor 1.0: A parallel pronoun-coreference corpus to support statistical MT, in: Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14), European Language Resources Association (ELRA), Reykjavik, Iceland. pp. 3191–3198. URL: http://www.lrec-conf.org/proceedings/lrec2014/pdf/298_Paper.pdf. ↗
  47. Hajičová, E., Vrbová, J., 1982. On the role of the hierarchy of activation in the process of natural language understanding, in: Proceedings of the 9th Conference on Computational Linguistics - Volume 1, Academia Praha, Czechoslovakia. pp. 107–113. URL: http://dx.doi.org/10.3115/991813.991830, doi:10.3115/991813.991830. ↗
  48. Haviland, S.E., Clark, H.H., 1974. What’s new? acquiring new information as a process in comprehension. Journal of Verbal Learning and Verbal Behavior 13, 512 – 521. URL: http://www.sciencedirect.com/science/article/pii/S0022537174800034, doi:https://doi.org/10.1016/S0022-5371(74) 80003-4. ↗
  49. He, W., Shao, Y., Zhang, P., 2020. Entity candidate network for whole-aware named entity recognition. arXiv preprint arXiv:2004.14145 . ↗
  50. Hirst, G., 1981. Anaphora in natural language understanding: A survey, in: Lecture Notes in Computer Science. find
  51. Hovy, E., Marcus, M., Palmer, M., Ramshaw, L., Weischedel, R., 2006. Ontonotes: the 90% solution, in: Proceedings of the human language technology conference of the NAACL, Companion Volume: Short Papers, pp. 57–60. find
  52. Ionita, M., Kashnitsky, Y., Krige, K., Larin, V., Atanasov, A., Logvinenko, D., 2019. Resolving gendered ambiguous pronouns with BERT, in: Proceedings of the First Workshop on Gender Bias in Natural Language Processing, Association for Computational Linguistics, Florence, Italy. pp. 113–119. URL: https://www.aclweb.org/anthology/W19-3817, doi:10.18653/v1/W19-3817. ↗
  53. Ji, Y., Tan, C., Martschat, S., Choi, Y., Smith, N.A., 2017. Dynamic entity representations in neural language models, in: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics, Copenhagen, Denmark. pp. 1830–1839. URL: https://www.aclweb.org/anthology/D17-1195, doi:10.18653/v1/ D17-1195. ↗
  54. Jonell, P., Bystedt, M., Dogan, F.I., Fallgren, P., Ivarsson, J., Slukova, M., Wennberg, U., Lopes, J., Boye, J., Skantze, G., 2018. Fantom: A crowdsourced social chatbot using an evolving dialog graph. Proc. Alexa Prize . find
  55. Joshi, M., Chen, D., Liu, Y., Weld, D.S., Zettlemoyer, L., Levy, O., 2020. Spanbert: Improving pre-training by representing and predicting spans. Transactions of the Association for Computational Linguistics 8, 64–77. ↗
  56. Joshi, M., Levy, O., Zettlemoyer, L., Weld, D., 2019. BERT for coreference resolution: Baselines and analysis, in: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Association for Computational Linguistics, Hong Kong, China. pp. 5803–5808. URL: https://www.aclweb.org/anthology/D19-1588, doi:10. 18653/v1/D19-1588. ↗
  57. Jurafsky, D., Martin, J.H., 2009. Speech and Language Processing (2Nd Edition). Prentice-Hall, Inc., Upper Saddle River, NJ, USA. find
  58. Kantor, B., Globerson, A., 2019. Coreference resolution with entity equalization, in: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 673–677.
  59. Kempson, R.M., 1977. Semantic Theory. Cambridge University Press. find
  60. Khosla, S., Rose, C., 2020. Using type information to improve entity coreference resolution. arXiv preprint arXiv:2010.05738 . ↗
  61. Kibble, R., van Deemter, K., 2000. Coreference annotation: Whither?, in: LREC. find
  62. Kingma, D.P., Ba, J., 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 . ↗
  63. Krause, T., Zeldes, A., 2014. Annis3: A new architecture for generic corpus query and visualization. Digital Scholarship in the Humanities 31, 118–139. ↗
  64. Krishna, M.H., Rahamathulla, K., Akbar, A., 2017. A feature based approach for sentiment analysis using svm and coreference resolution, in: 2017 International Conference on Inventive Communication and Computational Technologies (ICICCT), pp. 397–399. doi:10.1109/ICICCT.2017.7975227. ↗
  65. Krishna, R.M., Reddy, C.S., 2016. Extractive text summarization using lexical association and graph based text analysis, in: Computational Intelligence in Data Mining—Volume 1. Springer, pp. 261–272. find
  66. Kuhn, H.W., 1955. The hungarian method for the assignment problem. Naval Research Logistics Quarterly 2, 83–97. URL: https://onlinelibrary.wiley.com/doi/abs/10.1002/nav.3800020109, doi:10.1002/nav.3800020109, arXiv:https://onlinelibrary.wiley.com/doi/pdf/10.1002/nav.3800020109. ↗
  67. Kundu, G., Sil, A., Florian, R., Hamza, W., 2018. Neural cross-lingual coreference resolution and its application to entity linking, in: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), Association for Computational Linguistics, Melbourne, Australia. pp. 395–400. URL: https://www.aclweb.org/anthology/P18-2063, doi:10.18653/v1/P18-2063. ↗
  68. Kunz, J., Hardmeier, C., 2019. Entity decisions in neural language modelling: Approaches and problems, in: Proceedings of the Second Workshop on Computational Models of Reference, Anaphora and Coreference, pp. 15–19. find
  69. Kurita, K., Vyas, N., Pareek, A., Black, A.W., Tsvetkov, Y., 2019. Measuring bias in contextualized word representations, in: Proceedings of the First Workshop on Gender Bias in Natural Language Processing, Association for Computational Linguistics, Florence, Italy. pp. 166–172. URL: https://www.aclweb.org/anthology/W19-3823, doi:10.18653/v1/W19-3823. ↗
  70. Lappin, S., Leass, H.J., 1994. An algorithm for pronominal anaphora resolution. Comput. Linguist. 20, 535–561. URL: http://dl.acm.org/citation.cfm?id=203987.203989. ↗
  71. Lapshinova-Koltunski, E., Hardmeier, C., Krielke, P., 2018. ParCorFull: a parallel corpus annotated with full coreference, in: Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), European Language Resources Association (ELRA), Miyazaki, Japan. URL: https://www.aclweb.org/anthology/L18-1065. ↗
  72. Lata, K., Singh, P., Dutta, K., 2020. A comprehensive review on feature set used for anaphora resolution. Artificial Intelligence Review , 1–90. ↗
  73. Le, P., Titov, I., 2017. Optimizing differentiable relaxations of coreference evaluation metrics, in: Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017), Association for Computational Linguistics, Vancouver, Canada. pp. 390–399. URL: https://www.aclweb.org/anthology/K17-1039, doi:10.18653/v1/K17-1039. ↗
  74. Le, T.T., Vo, T.H., Mai, D.T., Quan, T.T., Phan, T.T., 2016. Sentiment analysis using anaphoric coreference resolution and ontology inference, in: International Workshop on Multi-disciplinary Trends in Artificial Intelligence, Springer. pp. 297–303. find
  75. Lee, H., Peirsman, Y., Chang, A., Chambers, N., Surdeanu, M., Jurafsky, D., 2011. Stanford’s multi-pass sieve coreference resolution system at the conll-2011 shared task, in: Proceedings of the fifteenth conference on computational natural language learning: Shared task, Association for Computational Linguistics. pp. 28–34.
  76. Lee, K., He, L., Lewis, M., Zettlemoyer, L., 2017. End-to-end neural coreference resolution, in: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics, Copenhagen, Denmark. pp. 188–197. URL: https://www.aclweb.org/anthology/D17-1018, doi:10.18653/v1/D17-1018. ↗
  77. Lee, K., He, L., Zettlemoyer, L., 2018. Higher-order coreference resolution with coarse-to-fine inference, in: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), Association for Computational Linguistics, New Orleans, Louisiana. pp. 687–692. URL: https://www.aclweb.org/anthology/N18-2108, doi:10.18653/v1/N18-2108. ↗
  78. Levesque, H., Davis, E., Morgenstern, L., 2012. The winograd schema challenge, in: Thirteenth International Conference on the Principles of Knowledge Representation and Reasoning. find
  79. Li, B.Z., Stanovsky, G., Zettlemoyer, L., 2020. Active learning for coreference resolution using discrete annotation, in: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics, Online. pp. 8320–8331. URL: https://www.aclweb.org/anthology/2020.acl-main.738, doi:10.18653/v1/2020. acl-main.738. ↗
  80. Ling, X., Singh, S., Weld, D.S., 2015. Design challenges for entity linking. Transactions of the Association for Computational Linguistics 3, 315–328. URL: https://www.aclweb.org/anthology/Q15-1023, doi:10.1162/tacl\ _a\_00141. ↗
  81. Liu, B., 2019. Anonymized BERT: An augmentation approach to the gendered pronoun resolution challenge, in: Proceedings of the First Workshop on Gender Bias in Natural Language Processing, Association for Computational Linguistics, Florence, Italy. pp. 120–125. URL: https://www.aclweb.org/anthology/W19-3818, doi:10.18653/v1/W19-3818. ↗
  82. Liu, L., Song, Z., Zheng, X., 2020. Improving coreference resolution by leveraging entity-centric features with graph neural networks and second-order inference. arXiv preprint arXiv:2009.04639 . ↗
  83. Luan, Y., He, L., Ostendorf, M., Hajishirzi, H., 2018. Multi-task identification of entities, relations, and coreference for scientific knowledge graph construction, in: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics, Brussels, Belgium. pp. 3219–3232. URL: https://www.aclweb.org/anthology/D18-1360, doi:10.18653/v1/D18-1360. ↗
  84. Luo, H., Glass, J., 2018. Learning word representations with cross-sentence dependency for end-to-end co-reference resolution, in: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 4829–4833. find
  85. Luo, X., 2005. On coreference resolution performance metrics, in: Proceedings of the Conference on Human Language Technology and Empirical Methods in Natural Language Processing, Association for Computational Linguistics, Stroudsburg, PA, USA. pp. 25–32. URL: https://doi.org/10.3115/1220575.1220579, doi:10.3115/1220575.1220579. ↗
  86. Luo, X., Ittycheriah, A., Jing, H., Kambhatla, N., Roukos, S., 2004. A mention-synchronous coreference resolution algorithm based on the bell tree, in: Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics, Association for Computational Linguistics. p. 135.
  87. Martschat, S., Göckel, T., Strube, M., 2015. Analyzing and visualizing coreference resolution errors, in: Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations, Association for Computational Linguistics, Denver, Colorado. pp. 6–10. URL: http://www.aclweb.org/anthology/N15-3002, doi:10.3115/v1/N15-3002. ↗
  88. Meng, Y., Rumshisky, A., 2018. Triad-based neural network for coreference resolution, in: Proceedings of the 27th International Conference on Computational Linguistics, Association for Computational Linguistics, Santa Fe, New Mexico, USA. pp. 35–43. URL: https://www.aclweb.org/anthology/C18-1004. ↗
  89. Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J., 2013. Distributed representations of words and phrases and their compositionality, in: Advances in neural information processing systems, pp. 3111–3119.
  90. Mitkov, R., 1999. Anaphora resolution: the state of the art, Citeseer. find
  91. Miyato, T., Dai, A.M., Goodfellow, I., 2016. Adversarial training methods for semi-supervised text classification. arXiv preprint arXiv:1605.07725 . ↗
  92. Moher, D., Liberati, A., Tetzlaff, J., Altman, D.G., Group, P., et al., 2009. Preferred reporting items for systematic reviews and meta-analyses: the prisma statement. PLoS med 6, e1000097. ↗
  93. Moosavi, N.S., Strube, M., 2016. Which coreference evaluation metric do you trust? a proposal for a link-based entity aware metric, in: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Association for Computational Linguistics. pp. 632–642. URL: http://aclweb.org/anthology/P16-1060, doi:10.18653/ v1/P16-1060. ↗
  94. Moosavi, N.S., Strube, M., 2017. Lexical features in coreference resolution: To be used with caution, in: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), Association for Computational Linguistics, Vancouver, Canada. pp. 14–19. URL: https://www.aclweb.org/anthology/P17-2003, doi:10.18653/v1/P17-2003. ↗
  95. Moosavi, N.S., Strube, M., 2018. Using linguistic features to improve the generalization capability of neural coreference resolvers, in: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 193–203.
  96. Müller, C., Strube, M., 2006. Multi-level annotation of linguistic data with mmax2. Corpus technology and language pedagogy: New resources, new tools, new methods 3, 197–214. find
  97. Nair, V., Hinton, G.E., 2010. Rectified linear units improve restricted boltzmann machines, in: Proceedings of the 27th International Conference on International Conference on Machine Learning, Omnipress, USA. pp. 807–814. URL: http://dl.acm.org/citation.cfm?id=3104322.3104425. ↗
  98. Ng, V., 2010. Supervised noun phrase coreference research: The first fifteen years, in: Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics, Stroudsburg, PA, USA. pp. 1396–1411. URL: http://dl.acm.org/citation.cfm?id=1858681.1858823. ↗
  99. Ng, V., Cardie, C., 2002. Identifying anaphoric and non-anaphoric noun phrases to improve coreference resolution, in: COLING 2002: The 19th International Conference on Computational Linguistics. find
  100. Nissim, M., Dingare, S., Carletta, J., Steedman, M., 2004. An annotation scheme for information status in dialogue. Proceedings of the 4th International Conference on Language Resources and Evaluation , 1023–1026. find
  101. Pennington, J., Socher, R., Manning, C., 2014. Glove: Global vectors for word representation, in: Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), pp. 1532–1543. ↗
  102. Peters, M.E., Neumann, M., Iyyer, M., Gardner, M., Clark, C., Lee, K., Zettlemoyer, L., 2018. Deep contextualized word representations, in: Proc. of NAACL.
  103. Plu, J., 2016. Knowledge extraction in web media: at the frontier of nlp, machine learning and semantics, in: Proceedings of the 25th International Conference Companion on World Wide Web, International World Wide Web Conferences Steering Committee. pp. 317–322. find
  104. Plu, J., Prokofyev, R., Tonon, A., Cudré-Mauroux, P., Difallah, D.E., Troncy, R., Rizzo, G., 2018. Sanaphor++: Combining deep neural networks with semantics for coreference resolution, in: Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC-2018). find
  105. Poesio, M., Stuckardt, R., Versley, Y., 2016. Anaphora resolution. Springer. find
  106. Popescu-Belis, A., 2019. Context in neural machine translation: A review of models and evaluations. arXiv preprint arXiv:1901.09115 . ↗
  107. Pradhan, S., Luo, X., Recasens, M., Hovy, E., Ng, V., Strube, M., 2014. Scoring coreference partitions of predicted mentions: A reference implementation. Proceedings of the conference. Association for Computational Linguistics. Meeting 2014, 30—35. URL: http://europepmc.org/articles/PMC5667668, doi:10.3115/v1/P14-2006. ↗
  108. Pradhan, S., Moschitti, A., Xue, N., Uryupina, O., Zhang, Y., 2012. Conll-2012 shared task: Modeling multilingual unrestricted coreference in ontonotes, in: Joint Conference on EMNLP and CoNLL - Shared Task, Association for Computational Linguistics, Stroudsburg, PA, USA. pp. 1–40. URL: http://dl.acm.org/citation.cfm?id=2391181.2391183. ↗
  109. Pradhan, S., Ramshaw, L., Marcus, M., Palmer, M., Weischedel, R., Xue, N., 2011. Conll-2011 shared task: Modeling unrestricted coreference in ontonotes, in: Proceedings of the Fifteenth Conference on Computational Natural Language Learning: Shared Task, Association for Computational Linguistics, Portland, Oregon, USA. pp. 1–27. URL: http://www.aclweb.org/anthology/W11-1901. ↗
  110. Prange, J., Schneider, N., Abend, O., 2019. Semantically constrained multi-layer annotation: The case of coreference, in: Proceedings of the First International Workshop on Designing Meaning Representations, Association for Computational Linguistics, Florence, Italy. pp. 164–176. URL: https://www.aclweb.org/anthology/W19-3319, doi:10.18653/v1/W19-3319. ↗
  111. Prince, E.F., 1981. Toward a taxonomy of given-new information, in: Cole, P. (Ed.), Syntax and semantics: Vol. 14. Radical Pragmatics. Academic Press, New York, pp. 223–255. find
  112. Prokofyev, R., Tonon, A., Luggen, M., Vouilloz, L., Difallah, D.E., Cudré-Mauroux, P., 2015. Sanaphor: Ontology-based coreference resolution, in: International Semantic Web Conference, Springer. pp. 458–473. find
  113. Rahman, A., Ng, V., 2009. Supervised models for coreference resolution, in: Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 2-Volume 2, Association for Computational Linguistics. pp. 968–977.
  114. Ratinov, L., Roth, D., 2012. Learning-based multi-sieve co-reference resolution with knowledge, in: Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Association for Computational Linguistics. pp. 1234–1244.
  115. Recasens, M., Hovy, E.H., 2011. Blanc: Implementing the rand index for coreference evaluation. Natural Language Engineering 17, 485–510. ↗
  116. Recasens, M., de Marneffe, M.C., Potts, C., 2013. The life and death of discourse entities: Identifying singleton mentions, in: Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Association for Computational Linguistics, Atlanta, Georgia. pp. 627–633. URL: https://www.aclweb.org/anthology/N13-1071. ↗
  117. Rudinger, R., Naradowsky, J., Leonard, B., Van Durme, B., 2018. Gender bias in coreference resolution, in: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), Association for Computational Linguistics, New Orleans, Louisiana. pp. 8–14. URL: https://www.aclweb.org/anthology/N18-2002, doi:10.18653/v1/N18-2002. ↗
  118. Saunders, D., Sallis, R., Byrne, B., 2020. Neural machine translation doesn’t translate gender coreference right unless you make it. arXiv preprint arXiv:2010.05332 . ↗
  119. Song, S., Huang, H., Ruan, T., 2019. Abstractive text summarization using lstm-cnn based deep learning. Multimedia Tools and Applications 78, 857– 875. find
  120. Soon, W.M., Ng, H.T., Lim, D.C.Y., 2001. A machine learning approach to coreference resolution of noun phrases. Computational linguistics 27, 521– 544. ↗
  121. Stoyanov, V., Eisner, J., 2012. Easy-first coreference resolution, in: Proceedings of COLING 2012, pp. 2519–2534.
  122. Stoyanov, V., Gilbert, N., Cardie, C., Riloff, E., 2009. Conundrums in noun phrase coreference resolution: Making sense of the state-of-the-art, in: Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP, Association for Computational Linguistics. pp. 656–664. URL: http://aclweb.org/anthology/P09-1074. ↗
  123. Stylianou, N., Vlahavas, I., 2020. E.T.: Entity-transformers. coreference augmented neural language model for richer mention representations via entity-transformer blocks, in: Proceedings of the Third Workshop on Computational Models of Reference, Anaphora and Coreference, Association for Computational Linguistics, Barcelona, Spain (online). pp. 1–10. URL: https://www.aclweb.org/anthology/2020.crac-1.1. ↗
  124. Subramanian, S., Roth, D., 2019. Improving generalization in coreference resolution via adversarial training, in: Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (* SEM 2019), pp. 192–197.
  125. Sukthanker, R., Poria, S., Cambria, E., Thirunavukarasu, R., 2018. Anaphora and coreference resolution: A review. CoRR abs/1805.11824. URL: http://arxiv.org/abs/1805.11824, arXiv:1805.11824. ↗
  126. Swayamdipta, S., Thomson, S., Lee, K., Zettlemoyer, L., Dyer, C., Smith, N.A., 2018. Syntactic scaffolds for semantic structures, in: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics, Brussels, Belgium. pp. 3772–3782. URL: https://www.aclweb.org/anthology/D18-1412. ↗
  127. Teh, Y., Bapst, V., Czarnecki, W.M., Quan, J., Kirkpatrick, J., Hadsell, R., Heess, N., Pascanu, R., 2017. Distral: Robust multitask reinforcement learning, in: Advances in Neural Information Processing Systems, pp. 4496–4506. find
  128. Tenney, I., Xia, P., Chen, B., Wang, A., Poliak, A., McCoy, R.T., Kim, N., Van Durme, B., Bowman, S.R., Das, D., et al., 2019. What do you learn from context? probing for sentence structure in contextualized word representations. arXiv preprint arXiv:1905.06316 . ↗
  129. Tieleman, T., Hinton, G., 2012. Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude. COURSERA: Neural networks for machine learning 4, 26–31. find
  130. Toshniwal, S., Wiseman, S., Ettinger, A., Livescu, K., Gimpel, K., 2020. Learning to ignore: Long document coreference with bounded memory neural networks. arXiv preprint arXiv:2010.02807 . ↗
  131. Urbizu, G., Soraluze, A., Arregi, O., 2019. Deep cross-lingual coreference resolution for less-resourced languages: The case of basque, in: Proceedings of the Second Workshop on Computational Models of Reference, Anaphora and Coreference, Association for Computational Linguistics, Minneapolis, USA. pp. 35–41. URL: https://www.aclweb.org/anthology/W19-2806, doi:10.18653/v1/W19-2806. ↗
  132. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., Polosukhin, I., 2017. Attention is all you need, in: Advances in neural information processing systems, pp. 5998–6008.
  133. Vilain, M., Burger, J., Aberdeen, J., Connolly, D., Hirschman, L., 1995. A model-theoretic coreference scoring scheme, in: Proceedings of the 6th Conference on Message Understanding, Association for Computational Linguistics, Stroudsburg, PA, USA. pp. 45–52. URL: https://doi.org/10.3115/1072399.1072405, doi:10.3115/1072399.1072405. ↗
  134. Voita, E., Serdyukov, P., Sennrich, R., Titov, I., 2018. Context-aware neural machine translation learns anaphora resolution, in: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Association for Computational Linguistics, Melbourne, Australia. pp. 1264–1274. URL: https://www.aclweb.org/anthology/P18-1117, doi:10.18653/v1/P18-1117. ↗
  135. Wang, Y., Wang, M., Fujita, H., 2020. Word sense disambiguation: A comprehensive knowledge exploitation framework. Knowledge-Based Systems 190, 105030. ↗
  136. Webster, K., Curran, J.R., 2014. Limited memory incremental coreference resolution, in: Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers, pp. 2129–2139.
  137. Webster, K., Recasens, M., Axelrod, V., Baldridge, J., 2018. Mind the GAP: A balanced corpus of gendered ambiguous pronouns. CoRR abs/1810.05201. URL: http://arxiv.org/abs/1810.05201, arXiv:1810.05201. ↗
  138. Weischedel, R., Palmer, M., Marcus, M., Hovy, E., 2007. Ontonotes release 2.0 with ontonotes db tool v. 0.92 beta and ontoviewer v. 0.9 beta. find
  139. Weischedel, R., Palmer, M., Marcus, M., Hovy, E., Pradhan, S., Ramshaw, L., Xue, N., Taylor, A., Kaufman, J., Franchini, M., et al., 2013. Ontonotes release 5.0 ldc2013t19. Linguistic Data Consortium, Philadelphia, PA 23. find
  140. Wiseman, S., Rush, A.M., Shieber, S., Weston, J., 2015. Learning anaphoricity and antecedent ranking features for coreference resolution, in: 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), Association for Computational Linguistics, Beijing, China. pp. 1416–1426. URL: https://www.aclweb.org/anthology/P15-1137, doi:10.3115/v1/P15-1137. ↗
  141. Wiseman, S., Rush, A.M., Shieber, S.M., 2016. Learning global features for coreference resolution, in: Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Association for Computational Linguistics, San Diego, California. pp. 994–1004. URL: https://www.aclweb.org/anthology/N16-1114, doi:10.18653/v1/N16-1114. ↗
  142. Wu, W., Wang, F., Yuan, A., Wu, F., Li, J., 2020. CorefQA: Coreference resolution as query-based span prediction, in: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics, Online. pp. 6953–6963. URL: https://www.aclweb.org/anthology/2020.acl-main.622, doi:10.18653/ v1/2020.acl-main.622. ↗
  143. Xia, P., Sedoc, J., Van Durme, B., 2020. Revisiting memory-efficient incremental coreference resolution. arXiv preprint arXiv:2005.00128 . ↗
  144. Xu, L., Choi, J.D., 2020. Revealing the myth of higher-order inference in coreference resolution. arXiv preprint arXiv:2009.12013 . ↗
  145. Xu, Y., Yang, J., 2019. Look again at the syntax: Relational graph convolutional network for gendered ambiguous pronoun resolution, in: Proceedings of the First Workshop on Gender Bias in Natural Language Processing, Association for Computational Linguistics, Florence, Italy. pp. 96–101. URL: https://www.aclweb.org/anthology/W19-3814, doi:10.18653/v1/W19-3814. ↗
  146. Yang, X., Zhou, G., Su, J., Tan, C.L., 2003. Coreference resolution using competition learning approach, in: Proceedings of the 41st Annual Meeting on Association for Computational Linguistics-Volume 1, Association for Computational Linguistics. pp. 176–183.
  147. Yang, Z., Blunsom, P., Dyer, C., Ling, W., 2017. Reference-aware language models, in: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics, Copenhagen, Denmark. pp. 1850–1859. URL: https://www.aclweb.org/anthology/D17-1197, doi:10.18653/v1/D17-1197. ↗
  148. Yangy, X., Su, J., Zhou, G., Tan, C.L., 2004. An np-cluster based approach to coreference resolution, in: Proceedings of the 20th international conference on Computational Linguistics, Association for Computational Linguistics. p. 226.
  149. Zeldes, A., 2017. The gum corpus: creating multilayer resources in the classroom. Language Resources and Evaluation 51, 581–612. doi:10.1007/ s10579-016-9343-x. ↗
  150. Zhang, H., Song, Y., Song, Y., 2019a. Incorporating context and external knowledge for pronoun coreference resolution, in: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), Association for Computational Linguistics, Minneapolis, Minnesota. pp. 872–881. URL: https://www.aclweb.org/anthology/N19-1093, doi:10.18653/v1/N19-1093. ↗
  151. Zhang, H., Song, Y., Song, Y., Yu, D., 2019b. Knowledge-aware pronoun coreference resolution, in: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics, Florence, Italy. pp. 867–876. URL: https://www.aclweb.org/anthology/P19-1083, doi:10.18653/v1/P19-1083. ↗
  152. Zhang, R., Nogueira dos Santos, C., Yasunaga, M., Xiang, B., Radev, D., 2018. Neural coreference resolution with deep biaffine attention by joint mention detection and mention clustering, in: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), Association for Computational Linguistics, Melbourne, Australia. pp. 102– 107. URL: https://www.aclweb.org/anthology/P18-2017. ↗
  153. Zhao, J., Wang, T., Yatskar, M., Cotterell, R., Ordonez, V., Chang, K.W., 2019. Gender bias in contextualized word embeddings, in: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), Association for Computational Linguistics, Minneapolis, Minnesota. pp. 629–634. URL: https://www.aclweb.org/anthology/N19-1064, doi:10.18653/v1/N19-1064. ↗
  154. Zhao, J., Wang, T., Yatskar, M., Ordonez, V., Chang, K.W., 2018. Gender bias in coreference resolution: Evaluation and debiasing methods, in: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), Association for Computational Linguistics, New Orleans, Louisiana. pp. 15–20. URL: https://www.aclweb.org/anthology/N18-2003, doi:10. 18653/v1/N18-2003. ↗
  155. Zhu, P., Zhang, Z., Li, J., Huang, Y., Zhao, H., 2018. Lingke: a fine-grained multi-turn chatbot for customer service, in: Proceedings of the 27th International Conference on Computational Linguistics: System Demonstrations, Association for Computational Linguistics, Santa Fe, New Mexico. pp. 108– 112. URL: https://www.aclweb.org/anthology/C18-2024. ↗

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/stylianou-2019-neural-entity-coreference-resolution-review/