Advertisement

LM Enhanced BiRNN-CRF for Joint Chinese Word Segmentation and POS Tagging

  • Jianhu Zhang
  • Gongshen LiuEmail author
  • Jie Zhou
  • Cheng Zhou
  • Huanrong Sun
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11109)

Abstract

Word segmentation and part-of-speech tagging are two preliminary but fundamental components of Chinese natural language processing. With the upsurge of deep learning, end-to-end models are built without handcrafted features. In this work, we model Chinese word segmentation and part-of-speech tagging jointly on the basis of state-of-the-art BiRNN-CRF architecture. LSTM is adopted as the basic recurrent unit. Apart from utilizing pre-trained character embeddings and trigram features, we incorporate neural language model and conduct multi-task training. Highway layers are applied to tackle the discordance issue of the naive co-training. Experimental results on CTB5, CTB7, and PPD datasets show the effectiveness of the proposed method.

Keywords

Chinese word segmentation POS tagging LSTM Language model 

Notes

Acknowledgement

This research work has been funded by the National Natural Science Foundation of China (Grant No.61772337, U1736207 and 61472248), the SJTU-Shanghai Songheng Content Analysis Joint Lab, and program of Shanghai Technology Research Leader (Grant No.16XD1424400).

References

  1. 1.
    Abadi, M. et al.: Tensorflow: a system for large-scale machine learning. In: Proceedings of the 12th USENIX Conference on Operating Systems Design and Implementation, OSDI 2016, pp. 265–283. USENIX Association, Berkeley (2016)Google Scholar
  2. 2.
    Chen, X., Qiu, X., Huang, X.: A long dependency aware deep architecture for joint Chinese word segmentation and POS tagging. CoRR abs/1611.05384 (2016)Google Scholar
  3. 3.
    Chung, J., Gülçehre, Ç., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. CoRR abs/1412.3555 (2014)Google Scholar
  4. 4.
    Duchi, J., Hazan, E., Singer, Y.: Adaptive subgradient methods for online learning and stochastic optimization. J. Mach. Learn. Res. 12, 2121–2159 (2011)MathSciNetzbMATHGoogle Scholar
  5. 5.
    Durme, B.V., Rastogi, P., Poliak, A., Martin, M.P.: Efficient, compositional, order-sensitive n-gram embeddings. In: EACL (2017)Google Scholar
  6. 6.
    Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Teh, Y.W., Titterington, M. (eds.) Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, Proceedings of Machine Learning Research, PMLR, Chia Laguna Resort, Sardinia, Italy, vol. 9, pp. 249–256, 13–15 May 2010Google Scholar
  7. 7.
    Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997).  https://doi.org/10.1162/neco.1997.9.8.1735CrossRefGoogle Scholar
  8. 8.
    Jiang, W., Huang, L., Liu, Q., Lü, Y.: A cascaded linear model for joint chinese word segmentation and part-of-speech tagging. In: Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics (2008)Google Scholar
  9. 9.
    Jin, G., Chen, X.: The fourth international Chinese language processing bakeoff: Chinese word segmentation, named entity recognition and Chinese POS tagging. In: IJCNLP (2008)Google Scholar
  10. 10.
    Kruengkrai, C., Uchimoto, K., Kazama, J., Wang, Y., Torisawa, K., Isahara, H.: Joint Chinese word segmentation and POS tagging using an error-driven word-character hybrid model. IEICE Trans. Inf. Syst. E92(D12), 2298–2305 (2009).  https://doi.org/10.1587/transinf.E92.D.2298CrossRefGoogle Scholar
  11. 11.
    Lafferty, J.D., McCallum, A., Pereira, F.C.N.: Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: Proceedings of the Eighteenth International Conference on Machine Learning, ICML 2001, pp. 282–289. Morgan Kaufmann Publishers Inc., San Francisco (2001)Google Scholar
  12. 12.
    Li, B., Liu, T., Zhao, Z., Wang, P., Du, X.: Neural bag-of-ngrams. In: AAAI, pp. 3067–3074 (2017)Google Scholar
  13. 13.
    Li, Y., Li, W., Sun, F., Li, S.: Component-enhanced Chinese character embeddings. CoRR abs/1508.06669 (2015)Google Scholar
  14. 14.
    Ling, W., Luís, T., Marujo, L., Astudillo, R.F., Amir, S., Dyer, C., Black, A.W., Trancoso, I.: Finding function in form: Compositional character models for open vocabulary word representation. CoRR abs/1508.02096 (2015)Google Scholar
  15. 15.
    Liu, L., Shang, J., Xu, F.F., Ren, X., Gui, H., Peng, J., Han, J.: Empower sequence labeling with task-aware neural language model. CoRR abs/1709.04109 (2017)Google Scholar
  16. 16.
    Ma, X., Hovy, E.H.: End-to-end sequence labeling via bi-directional LSTM-CNNs-CRF. CoRR abs/1603.01354 (2016)Google Scholar
  17. 17.
    McCallum, A., Freitag, D., Pereira, F.C.N.: Maximum entropy markov models for information extraction and segmentation. In: Proceedings of the Seventeenth International Conference on Machine Learning, ICML 2000, pp. 591–598. Morgan Kaufmann Publishers Inc., San Francisco (2000)Google Scholar
  18. 18.
    Ng, H.T., Low, J.K.: Chinese part-of-speech tagging: one-at-a-time or all-at-once? word-based or character-based? In: Lin, D., Wu, D. (eds.) Proceedings of EMNLP 2004, pp. 277–284. Association for Computational Linguistics, Barcelona, July 2004Google Scholar
  19. 19.
    Pascanu, R., Mikolov, T., Bengio, Y.: Understanding the exploding gradient problem. CoRR abs/1211.5063 (2012)Google Scholar
  20. 20.
    Peng, F., Feng, F., McCallum, A.: Chinese segmentation and new word detection using conditional random fields. In: Proceedings of the 20th International Conference on Computational Linguistics, COLING 2004. Association for Computational Linguistics, Stroudsburg (2004).  https://doi.org/10.3115/1220355.1220436
  21. 21.
    Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: Empirical Methods in Natural Language Processing (EMNLP), pp. 1532–1543 (2014)Google Scholar
  22. 22.
    Peters, M.E., Ammar, W., Bhagavatula, C., Power, R.: Semi-supervised sequence tagging with bidirectional language models. CoRR abs/1705.00108 (2017)Google Scholar
  23. 23.
    Rei, M.: Semi-supervised multitask learning for sequence labeling. CoRR abs/1704.07156 (2017)Google Scholar
  24. 24.
    Shao, Y., Hardmeier, C., Tiedemann, J., Nivre, J.: Character-based joint segmentation and POS tagging for Chinese using bidirectional RNN-CRF. CoRR abs/1704.01314 (2017)Google Scholar
  25. 25.
    Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929–1958 (2014)MathSciNetzbMATHGoogle Scholar
  26. 26.
    Srivastava, R.K., Greff, K., Schmidhuber, J.: Highway networks. CoRR abs/1505.00387 (2015)Google Scholar
  27. 27.
    Sun, Y., Lin, L., Tang, D., Yang, N., Ji, Z., Wang, X.: Radical-enhanced Chinese character embedding. CoRR abs/1404.4714 (2014)Google Scholar
  28. 28.
    Uchiumi, K., Tsukahara, H., Mochihashi, D.: Inducing word and part-of-speech with Pitman-Yor hidden semi-Markov models. In: ACL (2015)Google Scholar
  29. 29.
    Vajjala, S., Banerjee, S.: A study of n-gram and embedding representations for native language identification. In: Proceedings of the 12th Workshop on Innovative Use of NLP for Building Educational Applications, pp. 240–248 (2017)Google Scholar
  30. 30.
    Wang, Y., Kazama, J., Tsuruoka, Y., Chen, W., Zhang, Y., Torisawa, K.: Improving Chinese word segmentation and POS tagging with semi-supervised methods using large auto-analyzed data. In: IJCNLP (2011)Google Scholar
  31. 31.
    Wieting, J., Bansal, M., Gimpel, K., Livescu, K.: Charagram: Embedding words and sentences via character n-grams. CoRR abs/1607.02789 (2016)Google Scholar
  32. 32.
    Yang, Z., Salakhutdinov, R., Cohen, W.W.: Transfer learning for sequence tagging with hierarchical recurrent networks. CoRR abs/1703.06345 (2017)Google Scholar
  33. 33.
    Zhang, Y., Clark, S.: Joint word segmentation and POS tagging using a single perceptron. In: Proceedings of ACL-08: HLT, pp. 888–896. Association for Computational Linguistics, Columbus, June 2008Google Scholar
  34. 34.
    Zhang, Y., Clark, S.: A fast decoder for joint word segmentation and POS-tagging using a single discriminative model. In: Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, EMNLP 2010, pp. 843–852. Association for Computational Linguistics, Stroudsburg (2010)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Jianhu Zhang
    • 1
  • Gongshen Liu
    • 1
    Email author
  • Jie Zhou
    • 1
  • Cheng Zhou
    • 2
  • Huanrong Sun
    • 2
  1. 1.School of Electric Information and Electronic EngineeringShanghai Jiaotong UniversityShanghaiChina
  2. 2.SJTU-Shanghai Songheng Content Analysis Joint LabShanghaiChina

Personalised recommendations