Elamur Research⌕
☰
home / papers / 2020 / Paraphrasing vs Coreferring: Two Sides of the Same Coin

Paraphrasing vs Coreferring: Two Sides of the Same Coin

Summary

Predicate paraphrase acquisition and cross-document event coreference resolution both deal with the same difficulty: different predicates can describe one event. Meged et al. show that each task can help the other. First, they re-score Chirps, a heuristically collected resource of predicate paraphrases mined from Twitter news headlines. Its original score relies only on how often, and on how many days, two templates were aligned. The authors build a supervised scorer called Chirps*, which uses a richer feature set. They train it with distant supervision derived semi-automatically from ECB+ coreference annotations. This raises average precision by over 18 points compared with the original ranking. Second, they turn the Chirps* features for a mention pair into an embedding and add it to the pairwise scorer of the state-of-the-art Barhom et al. (2019) coreference model. This gives small but statistically significant gains on every metric. The work matters because coreference-annotated data and paraphrase resources can reinforce each other, which motivates studying the two tasks jointly.

Key points

  • Chirps contains more than 5 million paraphrase pairs. It covers about 30% of lexically-divergent coreferring event pairs in ECB+, and more than 50% of the verbal ones (roughly 370 pairs in train and 200 in test).
  • The integration works as follows. A 17-dimensional Chirps* feature vector, or a zero vector when Chirps has no entry for the pair, goes through a small MLP (hidden layer 50, output 100). The result is concatenated with the original mention-pair vector of Barhom et al. (2019), which uses GloVe and ELMo.
  • On the ECB+ test set, CoNLL F1 rises from 79.5 to 80.0, compared with 76.5 for the lemma baseline. The largest gain is on MUC F1, from 80.9 to 81.61. The improvement is significant at p < 0.001.
  • Adding only the final Chirps* score, instead of the full feature vector, gave a smaller improvement.
  • Code is released on GitHub (yehudit96/coreferrability).

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

Fields: Machine translation

Topics: Coreference resolution

Cited by

22 papers of our library cite it (of the 140673 whose bibliographies we read); 8 of them have a page here, 14 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.2004.14979 · arXiv 2004.14979

@misc{meged2020paraphrasing,
  title = {{Paraphrasing vs Coreferring: Two Sides of the Same Coin}},
  author = {Meged, Yehudit and Caciularu, Avi and Shwartz, Vered and Dagan, Ido},
  year = {2020},
  doi = {10.48550/arxiv.2004.14979},
  eprint = {2004.14979},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2004.14979}
}

References

34 references, 17 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Amit Bagga and Breck Baldwin. 1998. Algorithms for scoring coreference chains. In The first international conference on language resources and evaluation workshop on linguistics coreference, volume 1, pages 563–566. Granada. find our card
  2. Shany Barhom, Vered Shwartz, Alon Eirew, Michael Bugert, Nils Reimers, and Ido Dagan. 2019. Revisiting joint modeling of cross-document entity and event coreference resolution. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4179–4189, Florence, Italy. Association for Computational Linguistics. find our card
  3. Regina Barzilay and Lillian Lee. 2003. Learning to paraphrase: An unsupervised approach using multiple-sequence alignment. In Proceedings of the 2003 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, pages 16–23. ↗ our card
  4. Regina Barzilay and Kathleen R. McKeown. 2001. Extracting paraphrases from a parallel corpus. In Proceedings of the 39th Annual Meeting of the Association for Computational Linguistics, pages 50–57, Toulouse, France. Association for Computational Linguistics. find our card
  5. Cosmin Bejan and Sanda Harabagiu. 2010. Unsupervised event coreference resolution with rich linguistic features. In Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, pages 1412–1422, Uppsala, Sweden. Association for Computational Linguistics. find our card
  6. Cosmin Adrian Bejan and Sanda Harabagiu. 2014. Unsupervised event coreference resolution. Computational Linguistics, 40(2):311–347. ↗ our card
  7. Jonathan Berant. 2012. Global Learning of Textual Entailment Graphs. Ph.D. thesis, Tel Aviv University. find
  8. Leo Breiman. 2001. Random forests. Machine learning, 45(1):5–32. find
  9. Prafulla Kumar Choubey and Ruihong Huang. 2017. Event coreference resolution by iteratively unfolding inter-dependencies among events. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2124–2133, Copenhagen, Denmark. Association for Computational Linguistics. find our card
  10. Agata Cybulska and Piek T. J. M. Vossen. 2014. Using a sledgehammer to crack a nut? lexical diversity and event coreference resolution. In LREC. find our card
  11. Bill Dolan, Chris Brockett, and Chris Quirk. 2005. Microsoft research paraphrase corpus. Retrieved March, 29(2008):63. find
  12. Rotem Dror, Gili Baumer, Segev Shlomov, and Roi Reichart. 2018. The hitchhiker’s guide to testing statistical significance in natural language processing. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1383–1392, Melbourne, Australia. Association for Computational Linguistics. find
  13. Juri Ganitkevitch, Benjamin Van Durme, and Chris Callison-Burch. 2013. Ppdb: The paraphrase database. In Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 758–764. find our card
  14. Matthew Honnibal and Ines Montani. 2017. Spacy. Natural language understanding with bloom embeddings, convolutional neural networks and incremental parsing. find
  15. Kian Kenyon-Dean, Jackie Chi Kit Cheung, and Doina Precup. 2018. Resolving event coreference with supervised representation learning and clustering-oriented regularization. In Proceedings of the Seventh Joint Conference on Lexical and Computational Semantics, pages 1–10, New Orleans, Louisiana. Association for Computational Linguistics. find our card
  16. Wuwei Lan, Siyu Qiu, Hua He, and Wei Xu. 2017. A continuously growing dataset of sentential paraphrases. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 1224–1234, Copenhagen, Denmark. Association for Computational Linguistics. find our card
  17. Heeyoung Lee, Marta Recasens, Angel Chang, Mihai Surdeanu, and Dan Jurafsky. 2012. Joint entity and event coreference resolution across documents. In Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pages 489–500, Jeju Island, Korea. Association for Computational Linguistics. find our card
  18. Dekang Lin and Patrick Pantel. 2001. DIRT - Discovery of inference rules from text. In Proceedings of the seventh ACM SIGKDD international conference on Knowledge discovery and data mining, pages 323–328. find
  19. Xiaoqiang Luo. 2005. On coreference resolution performance metrics. In Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, pages 25–32, Vancouver, British Columbia, Canada. Association for Computational Linguistics. ↗ our card
  20. Jonathan Mallinson, Rico Sennrich, and Mirella Lapata. 2017. Paraphrasing revisited with neural machine translation. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pages 881–893, Valencia, Spain. Association for Computational Linguistics. find our card
  21. George A Miller. 1995. Wordnet: a lexical database for english. Communications of the ACM, 38(11):39– 41. ↗ our card
  22. F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay. 2011. Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12:2825–2830. ↗
  23. Jeffrey Pennington, Richard Socher, and Christopher Manning. 2014. Glove: Global vectors for word representation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1532–1543, Doha, Qatar. Association for Computational Linguistics. ↗
  24. Matthew E Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, and Luke Zettlemoyer. 2018. Deep contextualized word representations. arXiv preprint arXiv:1802.05365. ↗
  25. Sameer Pradhan, Xiaoqiang Luo, Marta Recasens, Eduard Hovy, Vincent Ng, and Michael Strube. 2014. Scoring coreference partitions of predicted mentions: A reference implementation. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 30–35, Baltimore, Maryland. Association for Computational Linguistics. ↗ our card
  26. Marta Recasens, Matthew Can, and Daniel Jurafsky. 2013. Same referent, different words: Unsupervised mining of opaque coreferent mentions. In Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 897–906, Atlanta, Georgia. Association for Computational Linguistics. find
  27. Yusuke Shinyama and Satoshi Sekine. 2006. Preemptive information extraction using unrestricted relation discovery. In Proceedings of the Human Language Technology Conference of the NAACL, Main Conference, pages 304–311, New York City, USA. Association for Computational Linguistics. find
  28. Yusuke Shinyama, Satoshi Sekine, and Kiyoshi Sudo. 2002. Automatic paraphrase acquisition from news articles. In Proceedings of the second international conference on Human Language Technology Research, pages 313–318. Morgan Kaufmann Publishers Inc. find
  29. Vered Shwartz, Gabriel Stanovsky, and Ido Dagan. 2017. Acquiring predicate paraphrases from news tweets. In Proceedings of the 6th Joint Conference on Lexical and Computational Semantics (*SEM 2017), pages 155–160, Vancouver, Canada. Association for Computational Linguistics. find
  30. Idan Szpektor, Hristo Tanev, Ido Dagan, and Bonaventura Coppola. 2004. Scaling web-based acquisition of entailment relations. In Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing, pages 41–48. find
  31. Marc Vilain, John Burger, John Aberdeen, Dennis Connolly, and Lynette Hirschman. 1995. A model-theoretic coreference scoring scheme. In Proceedings of the 6th conference on Message understanding, pages 45–52. Association for Computational Linguistics. find our card
  32. Wei Xu, Alan Ritter, Chris Callison-Burch, William B Dolan, and Yangfeng Ji. 2014. Extracting lexically divergent paraphrases from twitter. Transactions of the Association for Computational Linguistics, 2:435–448. ↗
  33. Bishan Yang, Claire Cardie, and Peter Frazier. 2015. A hierarchical distance-dependent bayesian model for event coreference resolution. Transactions of the Association for Computational Linguistics, 3:517–528. ↗
  34. Congle Zhang and Daniel S Weld. 2013. Harvesting parallel news streams to generate paraphrases of event relations. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 1776–1786. find

↑ back to top

This page in Markdown →