No Access

Anaphoricity Determination of Anaphora Resolution in Uygur Pronoun Based on CNN-LSTM Model

Tian Shengwei

School of Software, Xinjiang University, 499 Xibei Road, Urumqi 830008, P. R. China

E-mail Address: tianshengwei@163.com

Search for more papers by this author

Li Dongbai

School of Software, Xinjiang University, 499 Xibei Road, Urumqi 830008, P. R. China

E-mail Address: db.li@cnnlper.cn

Search for more papers by this author

Yu Long

Net Center, Xinjiang University, 666 Shengli Road, Urumqi 830046, P. R. China

E-mail Address: yul_xju@163.com

Corresponding author.

Search for more papers by this author

Feng Guanjun

Faculty of Humanities, Xinjiang University, 666 Shengli Road, Urumqi 830046, P. R. China

E-mail Address: 343541228@qq.com

Search for more papers by this author

Zhao Jianguo

Chinese Language Institute, Xinjiang University, 666 Shengli Road, Urumqi 830046, P. R. China

E-mail Address: 690410683@qq.com

Search for more papers by this author

, and

Li Pu

Chinese Language Institute, Xinjiang University, 666 Shengli Road, Urumqi 830046, P. R. China

E-mail Address: Lipu1217@163.com

Search for more papers by this author

https://doi.org/10.1142/S146902681750016XCited by:1 (Source: Crossref)

Abstract

As a core subtask in anaphora resolution, anaphoricity determination has aroused the interest of researchers. However, in recent work, the influence caused by the deep semantic information and the context of the coreference elements have not been taken into account. In this paper, by combining the semantic feature of Uygur, we established a Convolutional Neural Network & Long Short-Term Memory (CNN_LSTM) model in determining the anaphoricity of Uygur pronoun. Firstly, the deep negative semantic feature representation is extracted via word2vec. Secondly, the shallow explicit feature representation of coreference elements is extracted by our system. Afterwards, two kinds of features are combined to recognize whether coreference element is referential or not. The results showed that the method we used can distinguish coreference element accurately, the ACC $^{+}$ score is 90.18% and the ACC $^{-}$ score is 89.93%, which are higher than ANN (Artificial Neural Network) and SVM (Support Vector Machine) respectively.

Keywords:

Remember to check out the Most Cited Articles!
Check out these titles in artificial intelligence!

References

1. V. Stoyanov et al., Conundrums in noun phrase coreference resolution, in Proc. The Joint Conference of the, Meeting of the ACL and the International Joint Conference, 2009, p. 656. Google Scholar
2. S. Bergsma, D. Lin and R. Goebel, Distributional Identification of Non-Referential Pronouns, in Proc., Meeting of the Association for Computational Linguistics Proc. ACL 2008 ( Columbus, 2008), pp. 10–18. Google Scholar
3. G. Zhou and F. Kong, Global learning of noun phrase anaphoricity in coreference resolution via label propagation, in Proc. Conf. Empirical Methods in Natural Language Processing (EMNLP), Singapore, 2009, Vol. 26, pp. 978–986. Google Scholar
4. V. Ng, Graph-cut-based anaphoricity determination for coreference resolution, in Proc. Human Language Technologies: The 2009 Conference of the North American Chapter of the Association for Computational Linguistics, 2009, pp. 575–583. Google Scholar
5. B. J. R. Hobbs, Pronoun resolution, J. Acm Sigart Bulletin. 61 (2010) 28–28. Google Scholar
6. F. Kong, G. Zhou and L. Qian, Dependency-driven anaphoricity determination for coreference resolution, in Proc. Int. Conf. Computational Linguistics (COLING 2010), Beijing, 2010, pp. 599–607. Google Scholar
7. S. Wiseman, A. M. Rush, S. M. Shieber and J. Weston, Learning anaphoricity and antecedent ranking features for coreference resolution, in Proc. of the ACL 2015, Beijing, 2015, pp. 1416–1426. Google Scholar
8. W. M. Soon, H. T. Ng and D. Lim, A machine learning approach to coreference resolution of noun phrase, J. Comput. Linguist. 27 (2001) 521–544. Crossref, Google Scholar
9. V. Ng and C. Cardie, Improving machine learning approaches to coreference resolution, in Proc. ACL 2002, Vol. 4, pp. 104–111. Google Scholar
10. X. F. Yang, J. Su and C. L. Tan, A twin-candidate model for learning-based anaphora resolution, J. Comput. Linguist. 34 (2008) 327–356. Crossref, Google Scholar
11. F. Kong, G. D. Zhou and Q. M. Zhu, Employing the centering theory in pronoun resolution from the semantic perspective, in Proc. EMNLP, 2009, pp. 987–996. Google Scholar
12. H. Lee, Y. Peirsman, A. Chang et al., Stanford’s multi-pass sieve coreference resolution system at the CoNLL-2011 shared task, in Proc. 15th Conf. Computational Natural Language Learning: Shared Task, 2011, pp. 28–34. Google Scholar
13. E. R. Fernandes, C. N. D. Santos and R. L. Milidiú, Latent structure perceptron with feature induction for unrestricted coreference resolution, in Proc. Joint Conf. EMNLP and CoNLL - Shared Task, 2012, pp. 41–48. Google Scholar
14. H. Lee, A. Chang, Y. Peirsman et al., Deterministic coreference resolution based on entity-centric, precision-ranked rules, J. Comput. Linguistics. 39 (2013) 885–916. Crossref, Google Scholar
15. K. Clark and C. D. Manning, Improving coreference resolution by learning entity-level distributed representations, J. arXiv preprint: 1606.01323, 2016. Google Scholar
16. T. Shengwei, Z. Jun and Y. Long, Automatic extraction of multi-word domain term in uyghur texts, J. Chinese Inf. Process. 29 (2015) 133–141. Google Scholar
17. J. Turian, L. Rationv and Y. Bengio, Word representations: A simple and general method for semi-supervised learning, in Proc. of the 48th Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics (ACL 2010) ( Uppsala, 2010), pp. 384–394. Google Scholar
18. S. Lai, K. Liu, S. He et al., How to generate a good word embedding, J. IEEE Intell. Syst. 31 (2016) 5–14. Crossref, Google Scholar
19. A. Mnih and G. Hinton, Three new graphical models for statistical language modelling, in Proc. 24th Int. Conf. Machine Learning (ACM, 2007), pp. 641–648. Google Scholar
20. R. Collobert and J. Weston, A unified architecture for natural language processing: Deep neural networks with multitask learning, in Proc. 25th Int. Conf. Machine Learning. (ACM, 2008), pp. 160–167. Google Scholar
21. E. H. Huang, R. Socher, C. D. Manning et al., Improving word representations via global context and multiple word prototypes, in Proc. 50th Annual Meeting of the Association for Computational Linguistics: Long Papers. Association for Computational Linguistics, Vol. 1 (2012), pp. 873–882. Google Scholar
22. T. Mikolov, K. Chen, G. Corrado et al., Efficient estimation of word representations in vector space, J. arXiv preprint arXiv: 1301.3181, 2013. Google Scholar
23. J. Pennington, R. Socher and C. D. Manning, Glove: Global vectors for word representation, in Proc. Empiricial Methods in Natural Language Process. (2014), pp. 1532–1543. Google Scholar
24. J. Wang, L. C. Yu, K. R. Lai et al., Dimensional sentiment analysis using a regional CNN-LSTM model, in Proc. Meeting Association for Computational Linguistics (2016), pp. 225–230. Google Scholar
25. W. Yih, X. He and C. Meek, Semantic parsing for single-relation question answering, in Proc. ACL 2014 (2014), pp. 643–648. Google Scholar
26. Y. Sun, L. Lin, D. Tang et al., Modeling mention, context and entity with neural networks for entity disambiguation, in Proc. Int. Conf. Artificial Intelligence (AAAI Press, 2015), pp. 1333–1339. Google Scholar
27. O. Abdel-Hamid, A. Mohamed, H. Jiang, et al., Convolutional reural networks for speech recognition, J. IEEE/ACM Transactions on Audio, Speech, and Language Processing 22 (2014) 1533–1545. Google Scholar
28. V. Nair and G. E. Hinton, Rectified linear units improve restricted boltzmann machines vinod nair, in Proc. Int. Conf. Machine Learning (2010), pp. 807–814. Google Scholar
29. R. Collobert, J. Weston, L. Bottou et al., Natural language processing (Almost) from scratch, J. Mach. Learn. Res. 12 (2011) 2493–2537. Google Scholar