Elamur Research⌕
☰
home / papers / 2018 / Entity-Centric Joint Modeling of Japanese Coreference Resolution and Predicate Argument Structure Analysis

Entity-Centric Joint Modeling of Japanese Coreference Resolution and Predicate Argument Structure Analysis

Summary

Japanese frequently omits arguments, which makes predicate argument structure analysis (PA) hard. Recovering an argument from earlier sentences (inter-sentential zero anaphora resolution, ZAR) is especially difficult because there are many candidates and no dependency path to the predicate. The authors argue that this requires knowing which entities are salient, and that salience only emerges when coreference resolution (CR) and PA are run together.

They build a neural joint model inspired by Wiseman et al. (2016). Basic phrases are encoded with a CNN and a Bi-LSTM. An entity buffer starts with the special entities author and reader and keeps one embedding per entity. The text is processed left to right: noun phrases go through CR and predicates through PA. Each decision considers both mentions and buffered entities, and each link updates the linked entity's embedding.

On Japanese News and Web evaluation sets, the model improves inter-sentential ZAR by a large margin over the baseline. This suggests that PA-only research in Japanese is insufficient. The authors expect the approach to carry over to Chinese, Korean, and other languages that likewise allow pronouns to be dropped.

Key points

  • The model covers four cases (NOM, ACC, DAT, NOM2) and handles intra-sentential, inter-sentential and exophora arguments, plus unspecified arguments.
  • For intra and exophora arguments of NOM/ACC/DAT on the same Web corpus, the model scores 0.626, compared with 0.534 for Shibata et al. (2016).
  • In the development-set ablation, removing string match drops CR F1 by about 0.42–0.43. Removing path embedding lowers News ZAR F1 by 0.188.
  • The NAIST text corpus was avoided because of annotation errors. CR on News (0.541) falls below Iida et al. (2003, about 0.7), but that work used compound nouns rather than nouns as its basic unit.
  • In error analysis, the authors attribute some errors to greedy left-to-right search. They name document-level reinforcement learning and bridging reference resolution as future work.

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: Linguistics & languages

Topics: Coreference resolution · Semantic role labeling

Cited by

10 papers of our library cite it (of the 140673 whose bibliographies we read); 2 of them have a page here, 8 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/p18-1054

@inproceedings{shibata2018entity,
  title = {{Entity-Centric Joint Modeling of Japanese Coreference Resolution and Predicate Argument Structure Analysis}},
  author = {Shibata, Tomohide and Kurohashi, Sadao},
  booktitle = {Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2018},
  doi = {10.18653/v1/p18-1054},
  url = {https://doi.org/10.18653/v1/p18-1054}
}

References

29 references, 10 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Mikael Henaff, Jason Weston, Arthur Szlam, Antoine Bordes, and Yann LeCun. 2016. Tracking the world state with recurrent entity networks. CoRR abs/1612.03969. http://arxiv.org/ abs/1612.03969. ↗
  2. Samy Bengio, Oriol Vinyals, Navdeep Jaitly, and Noam Shazeer. 2015. Scheduled sampling for sequence prediction with recurrent neural networks. CoRR abs/1506.03099. http://arxiv.org/ abs/1506.03099. ↗
  3. Ryu Iida, Kentaro Inui, Hiroya Takamura, and Yuji Matsumoto. 2003. Incorporating contextual cues in trainable models for coreference resolution. In In Proceedings of the EACL Workshop on The Computational Treatment of Anaphora. pages 23–30. find
  4. Chen Chen and Vincent Ng. 2016. Chinese zero pronoun resolution with deep neural networks. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, Berlin, Germany, pages 778–788. http://www. aclweb… find our card
  5. Ryu Iida, Kentaro Torisawa, Jong-Hoon Oh, Cana-sai Kruengkrai, and Julien Kloetzer. 2016. Intra-sentential subject zero anaphora resolution using multi-column convolutional neural network. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. Association for Comp… find our card
  6. Hugh Chen, Scott Lundberg, and Su-In Lee. 2017. Checkpoint ensembles: Ensemble methods from a single training process. CoRR abs/1710.03282. http://arxiv.org/abs/1710.03282. — [arXiv:1710.03282](https://arxiv.org/abs/1710.03282) ↗
  7. Yangfeng Ji, Chenhao Tan, Sebastian Martschat, Yejin Choi, and Noah A. Smith. 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, pages 1831–1840. http://… find
  8. Kevin Clark and Christopher D. Manning. 2015. Entity-centric coreference resolution with model stacking. In Association for Computational Linguistics (ACL). find our card
  9. Kevin Clark and Christopher D. Manning. 2016a. Deep reinforcement learning for mention-ranking coreference models. In Empirical Methods on Natural Language Processing (EMNLP). find our card
  10. Diederik P. Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. CoRR abs/1412.6980. http://arxiv.org/abs/ 1412.6980. ↗
  11. Kevin Clark and Christopher D. Manning. 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, pages 6… find our card
  12. Sosuke Kobayashi, Ran Tian, Naoaki Okazaki, and Kentaro Inui. 2016. Dynamic entity representation with max-pooling improves machine reading. In Proceedings of the NAACL HLT 2016. find
  13. Kenton Lee, Luheng He, Mike Lewis, and Luke Zettlemoyer. 2017. End-to-end neural coreference resolution. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, pages 188–197. http://www.aclweb.org/ anthology/D17-1018. ↗ our card
  14. Masatsugu Hangyo, Daisuke Kawahara, and Sadao Kurohashi. 2012. Building a diverse document leads corpus annotated with semantic relations. In Proceedings of the 26th Pacific Asia Conference on Language, Information, and Computation. Faculty of Computer Science, Universitas Indonesia, Bali,Indonesia,… find
  15. Yuichiroh Matsubayashi and Kentaro Inui. 2017. Revisiting the design issues of local models for japanese predicate-argument structure analysis. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers). Asian Federation of Natural Language Pr… find
  16. Masatsugu Hangyo, Daisuke Kawahara, and Sadao Kurohashi. 2013. Japanese zero reference resolution considering exophora and author/reader mentions. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Seattle, Washington… find
  17. Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Distributed representations of words and phrases and their compositionality. In C.J.C. Burges, L. Bottou, M. Welling, Z. Ghahramani, and K.Q. Weinberger, editors, Advances in Neural Information Processing Systems 26, Curr… find
  18. Luheng He, Kenton Lee, Mike Lewis, and Luke Zettlemoyer. 2017. Deep semantic role labeling: What works and what’s next. In Proceedings of the Annual Meeting of the Association for Computational Linguistics. find our card
  19. Hiroki Ouchi, Hiroyuki Shindo, Kevin Duh, and Yuji Matsumoto. 2015. Joint case argument identification for Japanese predicate argument structure analysis. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural… find
  20. Qingyu Yin, Yu Zhang, Weinan Zhang, and Ting Liu. 2017. Chinese zero pronoun resolution with deep memory network. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Copenhagen, Denmark, pages 1320–1329. https://www.ac… ↗ our card
  21. Hiroki Ouchi, Hiroyuki Shindo, and Yuji Matsumoto. 2017. Neural modeling of multi-predicate interactions for Japanese predicate argument structure analysis. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computation… find
  22. Shanheng Zhao and Hwee Tou Ng. 2007. Identification and resolution of Chinese zero pronouns: A machine learning approach. In Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL). Association for Computa… find our card
  23. Michael Roth and Mirella Lapata. 2016. Neural semantic role labeling with dependency path embeddings. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, Berlin, Germany, pages 1192–1202. http:… find
  24. Jie Zhou and Wei Xu. 2015. End-to-end learning of semantic role labeling using recurrent neural networks. 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). Asso… find
  25. Ryohei Sasano, Daisuke Kawahara, and Sadao Kurohashi. 2007. Improving coreference resolution using bridging reference resolution and automatically acquired synonyms. In DAARC. find
  26. Ryohei Sasano and Sadao Kurohashi. 2011. A discriminative approach to Japanese zero anaphora resolution with large-scale lexicalized case frames. In Proceedings of 5th International Joint Conference on Natural Language Processing. Asian Federation of Natural Language Processing, Chiang Mai, Thailand… find our card
  27. Tomohide Shibata, Daisuke Kawahara, and Sadao Kurohashi. 2016. Neural network-based model for Japanese predicate argument structure analysis. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics,… find
  28. Hirotoshi Taira, Sanae Fujita, and Masaaki Nagata. 2008. A Japanese predicate argument structure analysis using decision lists. In Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Honolulu, Hawaii, pages 523–532. http:… find
  29. Sam Wiseman, Alexander M. Rush, and Stuart M. Shieber. 2016. Learning global features for find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/papers/shibata-2018-entity-centric-joint-modeling-japanese/