Abstract
Tibetan Word Segmentation is a basic and essential task in Tibetan Natural Language Processing workflow. Performance of TWS can directly affect many other downstream Tibetan NLP tasks since errors propagate in a multi-stage NLP pipeline. Traditionally the majority of researchers leverage linear statistical approaches to tackle Tibetan Word Segmentation, which often requires hand-crafted linguistic feature engineering with great care. In this work, we propose a neural network architecture for Tibetan Word Segmentation, which is a stacked combination of CNN, Bi-LSTM and CRF. By using tagged data for supervised learning and unlabeled data for representation learning, with no involvement in feature engineering, our model can produce promising performance on the test set, surpassing our baseline models by a large margin, and indicating the effectiveness of the proposed neural model.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Tsering, T.: Design of an interative Tibetan word segmentation and word registering system (1999)
Qi, K.: Tibetan word segmentation designed for information processing. J. Northwest Univ. Nationalities 4, 92–97 (2006)
Liu, H., et al.: Segt: a practical Tibetan word segmentation tool. J. Chin. Inf. Process. 26(1), 97–104 (2012)
Li, Y., et al.: Tip-las: an opensource Tibetan tokenization and pos-tagging system. J. Chin. Inf. Process. 29(6), 203–207 (2015). (in Chinese)
Li, Y., et al.: An hybrid Tibetan word segmentation with unsupervised features. J. Chin. Inf. Process. 31(2), 71–75 (2017)
Rabiner, L.R., Juang, B.: An introduction to hidden Markov models. IEEE ASSP Mag. 3(1), 4–16 (1986)
Lafferty, J.D., McCallum, A., Pereira, F.C.N.: Conditional Random Fields: probabilistic models for segmenting and labeling sequence data. In: Proceedings of the 18th International Conference on Machine Learning (2001)
Li, B., et al.: Deep learning based Tibetan word segmentation methods. Comput. Eng. Des. 1, 194–198 (2018)
Bengio, Y., et al.: A neural probabilistic language model. J. Mach. Learn. Res. 3, 1137–1155 (2003)
Xue, N.: Chinese word segmentation as character tagging. Int. J. Comput. Linguist. Chin. Lang. Process. 8, 29–48 (2003)
Tapanainen, P., Voutilainen, A.: Tagging accurately: don’t guess if you know. In: ANLP (1994)
Cun, Y.L., et al.: Handwritten digit recognition with a back-propagation network. Adv. Neural. Inf. Process. Syst. 2(2), 396–404 (1990)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: International Conference on Neural Information Processing Systems (2012)
Collobert, R., et al.: Natural language processing (almost) from scratch. J. Mach. Learn. Res. 12, 2493–2537 (2011)
Lample, G., et al.: Neural Architectures for Named Entity Recognition (2016)
Kim, Y., et al.: Character-aware neural language models. In: 30th AAAI Conference on Artificial Intelligence (2016)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Yao, K., et al.: Spoken language understanding using long short-term memory neural networks. In: 2014 IEEE Spoken Language Technology Workshop (SLT) (2014)
Sutton, C., McCallum, A., et al.: An introduction to conditional random fields. Found. Trends Mach. Learn. 4(4), 267–373 (2012)
Acknowledgments
This work was supported by Science and Technology Department of Qinghai Province (grant numbers: 2020-ZJ-Y05, 2020-ZJ-704) and The National Key Research and Development Program of China (grant number: 2017YFB1402200).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Duanzhu, S., Jiacuo, C., Jia, C. (2021). Revisiting Tibetan Word Segmentation with Neural Networks. In: Liu, M., Kit, C., Su, Q. (eds) Chinese Lexical Semantics. CLSW 2020. Lecture Notes in Computer Science(), vol 12278. Springer, Cham. https://doi.org/10.1007/978-3-030-81197-6_44
Download citation
DOI: https://doi.org/10.1007/978-3-030-81197-6_44
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-81196-9
Online ISBN: 978-3-030-81197-6
eBook Packages: Computer ScienceComputer Science (R0)