ETRI Journal

Electronics and Telecommunications Research Institute (한국전자통신연구원)
권호 표지
DOI QR코드

DOI QR Code

Mention Detection Using Pointer Networks for Coreference Resolution

  • Park, Cheoneum (Department of Computer Science, Kangwon National University) ;
  • Lee, Changki (Department of Computer Science, Kangwon National University) ;
  • Lim, Soojong (SW & Content Research Laboratory, ETRI)
  • Received : 2017.02.23
  • Accepted : 2017.07.19
  • Published : 2017.10.01
Download PDF
⟨ Previous Next ⟩

Abstract

A mention has a noun or noun phrase as its head and constructs a chunk that defines any meaning, including a modifier. Mention detection refers to the extraction of mentions from a document. In mentions, coreference resolution refers to determining any mentions that have the same meaning. Pointer networks, which are models based on a recurrent neural network encoder-decoder, outputs a list of elements corresponding to an input sequence. In this paper, we propose mention detection using pointer networks. This approach can solve the problem of overlapped mention detection, which cannot be solved by a sequence labeling approach. The experimental results show that the performance of the proposed mention detection approach is F1 of 80.75%, which is 8% higher than rule-based mention detection, and the performance of the coreference resolution has a CoNLL F1 of 56.67% (mention boundary), which is 7.68% higher than coreference resolution using rule-based mention detection.

Keywords

References

  1. H. Lee et al., "Deterministic Coreference Resolution Based on Entity-Centric, Precision-Ranked Rules," Comput. Linguist., vol. 39, no. 4, 2013, pp. 885-916. https://doi.org/10.1162/COLI_a_00152
  2. A. Haghighi and D. Klein, "Coreference Resolution in a Modular, Entity-Centered Model," Human Language Technol. Annu. Conf. North American Chapter Assoc. Comput. Linguistics, Los Angeles, CA, USA, June 1-6, 2010, pp. 385-393.
  3. C. Park et al., "Korean Coreference Resolution with Guided Mention Pair Model Using Deep Learning," ETRI J., vol. 38, no. 6, Dec. 2016, pp. 1207-1217. https://doi.org/10.4218/etrij.16.0115.0896
  4. O. Vinyals et al., "Pointer Networks," Adv. Neural Inform. Process. Syst., vol. 12, 2015, pp. 2692-2700.
  5. K. Cho et al., "Learning Phrase Representation Using RNN Encoder-Decoder for Statistical Machine Translation," Proc. of EMNLP '14, 2014.
  6. D. Bahdanau et al., "Neural Machine Translation by Jointly Learning to Align and Translate," Proc. ICLR '15, 2015, arXiv:1409.0473.
  7. I. Zitouni and R. Florian, "Mention Detection Crossing the Language Barrier," Proc. Conf. Empirical Methods Natural Language Process., Honolulu, HI, USA, Oct. 25-27, 2008, pp. 600-609.
  8. R. Florian, "Improving Mention Detection Robustness to Noisy Input," Proc. Conf. Empirical Methods Natural Language Process, Cambridge, MA, USA, Oct. 9-11, 2010, pp. 335-345.
  9. D. Roth and W. Yih, "Global Inference for Entity and Relation Identification via a Linear Programming Formulation," in Introduction to Statistical Relational Learning, Cambridge, MA, USA: MIT Press, 2007, pp. 553-580.
  10. Q. Li and H. Ji, "Incremental Joint Extraction of Entity Mentions and Relations," Proc. Annu. Meeting Assoc. Comput. Linguistics, Baltimore, MD, USA, June 23-25, 2014, pp. 402-412.
  11. Q. Li et al., "Constructing Information Neural Networks Using One Single Model," Proc. Conf. Empirical Methods Natural Language Process., Doha, Qatar, Oct. 25-29, 2014, pp. 1846-1851.
  12. T.H. Nguyen et al., "Toward Mention Detection Robustness with Recurrent Neural Networks," arXiv preprint, 2016, arXiv:1602.07749.
  13. C. Park and C. Lee. "Mention Detection Using Bidirectional LSTM-CRF Model," Proc. KIISE HCLT, Rep. of Korea, 2015, pp. 224-227.
  14. A. Soraluze et al., "Mention Detection: First Steps in the Development of a Basque Coreference Resolution System," KONVENS Conf. Natural language Process., Vienna, Austria, Sept. 19-21, 2012, pp. 128-136.
  15. J.K. Kummerfeld et al., "Mention Detection: Heuristics for the OntoNotes Annotations," Proc. Conf. Comput. Natural Language Learn.: Shared Task, Portland, OR, USA, June 23-24, 2011, pp. 102-106.
  16. C. Park and C. Lee, "Mention Detection in the Coreference Resolution Using the Deep Learning," Proc. KIISE and the KBS Joint Symp., Rep. of Korea, 2015.
  17. C. Lee, J. Kim, and J. Kim, "Korean Dependency Parsing using Deep Learning," Proc. KIISE HCLT, Rep. of Korea, 2014, pp. 87-91.
  18. R. Collobert et al., "Natural Language Processing (almost) from Scratch," J. Mach. Learn. Res., vol. 12, 2011, pp. 2493-2537.