Abstract
We present a novel and elegant deep learning solution to train a single joint model on multi-criteria corpora for Chinese Word Segmentation (CWS) challenge. Our innovative design requires no private layers in model architecture, instead, introduces two artificial tokens at the beginning and ending of input sentence to specify the required target criteria. The rest of the model including Long Short-Term Memory (LSTM) layer and Conditional Random Fields (CRFs) layer remains unchanged and is shared across all datasets, keeping the size of parameter collection minimal and constant. On Bakeoff 2005 and Bakeoff 2008 datasets, our innovative design has surpassed the previous multi-criteria learning results. Testing results on two out of four datasets even have surpassed the latest state-of-the-art single-criterion learning scores. To the best knowledge, our design is the first one that has achieved the latest state-of-the-art performance on such large-scale datasets. Source codes and corpora of this paper are available on GitHub (https://github.com/hankcs/multi-criteria-cws).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
http://www.sighan.org/bakeoff2003/score This script rounds a score to one decimal place.
References
Xue, N.: Chinese word segmentation as character tagging. IJCLCLP (2003)
Jin, K.L., Ng, H.T., Guo, W.: A maximum entropy approach to chinese word segmentation. In: Proceedings of the Fourth Sighan Workshop on Chinese Language Processing (2005)
Lafferty, J.D., Mccallum, A., Pereira, F.C.N.: Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In: Eighteenth International Conference on Machine Learning, pp. 282–289 (2001)
Peng, F., Feng, F., Mccallum, A.: Chinese segmentation and new word detection using conditional random fields, pp. 562–568 (2004)
Zheng, X., Chen, H., Xu, T.: Deep learning for Chinese word segmentation and POS tagging. EMNLP (2013)
Collobert, R., Weston, J., Bottou, L., Karlen, M., Kavukcuoglu, K., Kuksa, P.P.: Natural language processing (Almost) from scratch. J. Machine Learning Res. (2011)
Pei, W., Ge, T., Chang, B.: Max-margin tensor neural network for Chinese word segmentation. ACL (2014)
Chen, X., Qiu, X., Zhu, C., Liu, P., Huang, X.: Long short-term memory neural networks for Chinese word segmentation. EMNLP (2015)
Cai, D., Zhao, H.: Neural word segmentation learning for Chinese. ACL (2016)
Cai, D., Zhao, H., Zhang, Z., Xin, Y., Wu, Y., Huang, F.: Fast and Accurate Neural Word Segmentation for Chinese (April 2017). arXiv:1704.07047
Chen, X., Shi, Z., Qiu, X., Huang, X.: Adversarial multi-criteria learning for Chinese word segmentation. 1704 (2017). arXiv:1704.07556
Huang, C., Zhao, H.: Chinese word segmentation: a decade review. J. Chin. Inf. Process. 21(3), 8–19 (2007)
Tseng, H., Chang, P., Andrew, G., Jurafsky, D., Manning, C.: A conditional random field word segmenter for sighan bakeoff 2005, 168–171 (2005)
Zhao, H., Huang, C., Li, M., Lu, B.L.: Effective tag set selection in Chinese word segmentation via conditional random field modeling. PACLIC (2006)
Zhao, H., Huang, C.N., Li, M., Lu, B.L.: A unified character-based tagging framework for chinese word segmentation. Acm Trans. Asian Language Inf. Process. 9(2), 1–32 (2010)
Sun, X., Wang, H., Li, W.: Fast online training with frequency-adaptive learning rates for chinese word segmentation and new word detection, pp. 253–262 (2012)
Dong, C., Zhang, J., Zong, C., Hattori, M., Di, H.: Character-based LSTM-CRF with radical-level features for Chinese named entity recognition. NLPCC/ICCPOL (2016)
Li, Z., Chao, J., Zhang, M., Chen, W.: Coupled Sequence Labeling on Heterogeneous Annotations: POS Tagging as a Case Study. 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), Stroudsburg, PA, USA, Association for Computational Linguistics, pp. 1783–1792 (2015)
Chao, J., Li, Z., Chen, W., Zhang, M.: Exploiting heterogeneous annotations for Weibo word segmentation and POS tagging. NLPCC (2015)
Johnson, M., Schuster, M., Le, Q.V., Krikun, M., Wu, Y., Chen, Z., Thorat, N., Viégas, F.B., Wattenberg, M., Corrado, G., Hughes, M., Dean, J.: Google’s Multilingual Neural Machine Translation System - Enabling Zero-Shot Translation. cs.CL (2016)
Lample, G., Ballesteros, M., Subramanian, S., Kawakami, K., Dyer, C.: Neural architectures for named entity recognition. CoRR (2016)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Graves, A., Schmidhuber, J.: Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Networks 18(5–6), 602–610 (2005)
Neubig, G., Dyer, C., Goldberg, Y., Matthews, A., Ammar, W., Anastasopoulos, A., Ballesteros, M., Chiang, D., Clothiaux, D., Cohn, T., et al.: Dynet: the dynamic neural network toolkit. (2017) arXiv preprint arXiv:1701.03980
Emerson, T.: The second international chinese word segmentation bakeoff. In: Proceedings of the Fourth SIGHAN Workshop on Chinese Language Processing, Jeju Island, Korea, pp. 123–133 (2005)
MOE, P.: The fourth international chinese language processing bakeoff: Chinese word segmentation, named entity recognition and chinese pos tagging. In: Proceedings of the sixth SIGHAN workshop on Chinese language processing (2008)
Zhang, Y., Clark, S.: Chinese segmentation with a word-based perceptron algorithm. In: Czech Republic, Association for Computational Linguistics, pp. 840–847. Prague (2007)
Zhao, H., Kit, C.: Unsupervised segmentation helps supervised learning of character tagging for word segmentation and named entity recognition. In: The Sixth SIGHAN Workshop on Chinese Language Processing, pp. 106–111 (2008)
Sun, X., Zhang, Y., Matsuzaki, T., Tsuruoka, Y., Tsujii, J.: A discriminative latent variable chinese segmenter with hybrid word/character information, pp. 56–64 (2009)
Zhang, L., Wang, H., Sun, X., Mansur, M.: Exploring representations from unlabeled data with co-training for chinese word segmentation. In: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, Seattle, Washington, USA, Association for Computational Linguistics, pp. 311–321 (October 2013)
Chen, X., Qiu, X., Zhu, C., Huang, X.: Gated recursive neural network for Chinese word segmentation. ACL (2015)
Wang, C., Xu, B.: Convolutional neural network with word embeddings for chinese word segmentation. (2017). arXiv preprint arXiv:1711.04411
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
He, H., Wu, L., Yan, H., Gao, Z., Feng, Y., Townsend, G. (2019). Effective Neural Solution for Multi-criteria Word Segmentation. In: Satapathy, S., Bhateja, V., Das, S. (eds) Smart Intelligent Computing and Applications . Smart Innovation, Systems and Technologies, vol 105. Springer, Singapore. https://doi.org/10.1007/978-981-13-1927-3_14
Download citation
DOI: https://doi.org/10.1007/978-981-13-1927-3_14
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-1926-6
Online ISBN: 978-981-13-1927-3
eBook Packages: EngineeringEngineering (R0)