Neural recovery machine for Chinese dropped pronoun

Abstract

Dropped pronouns (DPs) are ubiquitous in prodrop languages like Chinese, Japanese etc. Previous work mainly focused on painstakingly exploring the empirical features for DPs recovery. In this paper, we propose a neural recovery machine (NRM) to model and recover DPs in Chinese to avoid the non-trivial feature engineering process. The experimental results show that the proposed NRM significantly outperforms the state-of-the-art approaches on two heterogeneous datasets. Further experimental results of Chinese zero pronoun (ZP) resolution show that the performance of ZP resolution can also be improved by recovering the ZPs to DPs.

Keywords

neural network / Chinese dropped pronoun recovery / Chinese zero pronoun resolution

References

[1] Wang L Y, Tu Z P, Zhang X J, Li H, Way A, Liu Q. A novel approach for dropped pronoun translation. In: Proceedings of the 15th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Lanuage Technologies. 2016, 983–993

[2] Baran E, Yang Y Q, Xue N W. Annotating dropped pronouns in Chinese newswire text. In: Proceedings of the 8th International Conference on Language Resources and Evaluation. 2012, 2795–2799

[3] Yang Y Q, Liu Y L, Xue N W. Recovering dropped pronouns from Chinese text messages. In: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference of the Asian Federation of Natural Language Processing. 2015, 309–313

[4] Cohen J. A coefficient of agreement for nominal scales. Journal of Educational and Psychological Measurement, 1960, 20(1): 37–46

[5] Ronan C, Jason W. A unified architecture for natural language processing: deep neural networks with multitask learning. In: Proceedings of the 25th International Conference on Machine Learning. 2008, 160–167

[6] Yin Q Y, Zhang W N, Zhang Y, Liu T. A deep neural network for Chinese zero pronoun resolution. In: Proceedings of the 26th International Joint Conferences on Artificial Intelligence. 2017, 3322–3328

[7] Sepp H, Jurgen S. Long short-term memory. Journal of Neural Computation, 1997, 9(8): 1735–1780

[8] Mikolov T, Sutskever I, Chen K, Corrado G, Dean J. Distributed representations of words and phrases and their compositionality. In: Proceedings of the 26th International Conference on Neural Information Processing Systems-Volume 2. 2013, 3111–3119

[9] Chang C C, Lin C J. V. LIBSVM: a library for support vector machines. ACM Transactions on Intelligent Systems and Technology, 2011, 2(3): 1–27

[10] Gao Y, Zhen Y, Li H J, Chua T S. Filtering of brand-related microblogs using social-smooth multiview embedding. IEEE Transactions on Multimedia, 2016, 18(10): 2115–2126

[11] Janez D. Statistical comparisons of classifiers over multiple data sets. Journal of Machine Learning Research, 2006, 7(1): 1–30

[12] Chen C, Ng V. Chinese zero pronoun resolution: a joint unsupervised discourse-aware model rivaling state-of-the-art resolvers. In: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference of the Asian Federation of Natural Language Processing. 2015, 320–326

[13] Yang Y Q, Xue N W. Chasing the ghost: recovering empty categories in the Chinese Treebank. In: Proceedings of the 23rd International Conference on Computational Linguistics. 2010, 1382–1390

[14] Cai S, Chiang D, Goldberg Y. Language-independent parsing with empty elements. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics. 2011, 212–216

[15] Xue N W, Yang Y Q. Dependency-based empty category detection via phrase structure trees. In: Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2013, 1051–1060

[16] Kong F, Zhou G D. A clause-level hybrid approach to Chinese empty element recovery. In: Proceedings of the 23rd International Joint Conferences on Artificial Intelligence. 2013, 2113–2119

[17] Xiang B, Luo X Q, Zhou B W. Enlisting the ghost: modeling empty categories for machine translation. In: Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics. 2013, 822–831

[18] Zhao S H, Ng H T. 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. 2007, 541–550

[19] Kong F, Zhou G D. A tree kernel-based unified framework for Chinese zero anaphora resolution. In: Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing. 2010, 882–891

[20] Chen C, Ng V. Chinese zero pronoun resolution: some recent advances. In: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing. 2013, 1360–1365

[21] Ryu I, Kentaro I, Yuji M. Zero-anaphora resolution by learning rich syntactic pattern features. ACM Transactions on Asian Language Information Processing, 2007, 6(4): 1

[22] Ryohei S, Sadao K. A discriminative approach to Japanese zero anaphora resolution with large-scale lexicalized case frames. In: Proceedings of the 5th International Joint Conference on Natural Language Processing. 2011, 758–766

[23] Kim Y J. Subject/object drop in the acquisition of Korean: a crosslinguistic comparison. Journal of East Asian Linguistics, 2000, 9(4): 325–351

[24] Kim K S, Choi S J, Park S B, Lee S J. A two-step zero pronoun resolution by reducing candidate cardinality. In: Proceedings of Pacific Rim International Conference on Artificial Intelligence. 2012, 194–205

[25] Chen C, Ng V. Chinese zero pronoun resolution: an unsupervised approach combining ranking and integer linear programming. In: Proceedings of AAAI Conference on Artificial Intelligence. 2014, 1622–1628

RIGHTS & PERMISSIONS

Higher Education Press and Springer-Verlag GmbH Germany, part of Springer Nature