Abstract
Manually annotating is important for statistical NLP models but time-consuming and labor-intensive. We describe a learning task that can use partially annotated data as the training data. Traditional supervised learning task is a special case of such task. Particularly, we adapt the perceptron algorithm to train Chinese word segmentation models. We mix conventional fully segmented Chinese sentences with partially annotated sentences as the training data. Partially annotated sentences can be automatically generated from the heterogeneous segmented corpora as well as naturally annotated data such as markup language sentences like wikitexts without any additional manual annotating. The experiments show that our method improves the performances of both supervised model and semi-supervised models.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Jiang, W., Meng, F., Liu, Q., Lü, Y.: Iterative annotation transformation with predict-self reestimation for Chinese word segmentation. In: Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Jeju Island, Korea, pp. 412–420. Association for Computational Linguistics (July 2012)
Sun, W., Wan, X.: Reducing approximation and estimation errors for Chinese lexical processing with heterogeneous annotations. In: Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics. Long Papers, Jeju Island, Korea, vol. 1, pp. 232–241. Association for Computational Linguistics (July 2012)
Fernandes, E., dos Santos, C., Milidiú, R.: Latent structure perceptron with feature induction for unrestricted coreference resolution. In: Joint Conference on EMNLP and CoNLL - Shared Task, Jeju Island, Korea, pp. 41–48. Association for Computational Linguistics (July 2012)
Collins, M.: Discriminative training methods for hidden markov models: theory and experiments with perceptron algorithms, pp. 1–8 (2002)
Klein, D., Manning, C.D.: A generative constituent-context model for improved grammar induction. In: Proceedings of 40th Annual Meeting of the Association for Computational Linguistics, Philadelphia, Pennsylvania, USA, pp. 128–135. Association for Computational Linguistics (July 2002)
Lou, X., Hamprecht, F.: Structured learning from partial annotations. arXiv:1206.6421 (June 2012)
Neubig, G., Mori, S.: Word-based partial annotation for efficient corpus construction. In: Calzolari, N., Choukri, K., Maegaard, B., Mariani, J., Odijk, J., Piperidis, S., Rosner, M., Tapias, D. (eds.) Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC 2010), Valletta, Malta. European Language Resources Association, ELRA (2010)
Tsuboi, Y., Kashima, H., Mori, S., Oda, H., Matsumoto, Y.: Training conditional random fields using incomplete annotations. In: Proceedings of the 22nd International Conference on Computational Linguistics (Coling 2008), Manchester, UK, pp. 897–904. Coling 2008 Organizing Committee (August 2008)
Mirroshandel, S.A., Nasr, A.: Active learning for dependency parsing using partially annotated sentences. In: Proceedings of the 12th International Conference on Parsing Technologies, Dublin, Ireland, pp. 140–149. Association for Computational Linguistics (October 2011)
Flannery, D., Miayo, Y., Neubig, G., Mori, S.: Training dependency parsers from partially annotated corpora. In: Proceedings of 5th International Joint Conference on Natural Language Processing, Chiang Mai, Thailand, pp. 776–784. Asian Federation of Natural Language Processing (November 2011)
Fernandes, E.R., Brefeld, U.: Learning from partially annotated sequences. In: Gunopulos, D., Hofmann, T., Malerba, D., Vazirgiannis, M. (eds.) ECML PKDD 2011, Part I. LNCS, vol. 6911, pp. 407–422. Springer, Heidelberg (2011)
Yu, C.N.J., Joachims, T.: Learning structural SVMs with latent variables. In: Proceedings of the 26th Annual International Conference on Machine Learning, ICML 2009, pp. 1169–1176. ACM, New York (2009)
Zettlemoyer, L., Collins, M.: Online learning of relaxed CCG grammars for parsing to logical form. In: Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL), Prague, Czech Republic, pp. 678–687. Association for Computational Linguistics (June 2007)
McClosky, D., Charniak, E., Johnson, M.: Effective self-training for parsing. In: Proceedings of the Human Language Technology Conference of the NAACL, Main Conference, New York City, USA, pp. 152–159. Association for Computational Linguistics (June 2006)
Sarkar, A.: Applying co-training methods to statistical parsing. In: Proceedings of the Second Meeting of the North American Chapter of the Association for Computational Linguistics on Language Technologies, NAACL 2001, Stroudsburg, PA, pp. 1–8. Association for Computational Linguistics (2001)
Jiang, W., Huang, L., Liu, Q.: Automatic adaptation of annotation standards: Chinese word segmentation and POS tagging - a case study. In: Proceedings of the 47th ACL, Suntec, Singapore, pp. 522–530. Association for Computational Linguistics (August 2009)
Feng, H., Chen, K., Deng, X., Zheng, W.: Accessor variety criteria for Chinese word extraction. Computational Linguistics 30(1), 75–93 (2004)
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, W., Xu, J.: Enhancing Chinese word segmentation using unlabeled data. In: Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing, Edinburgh, Scotland, UK, pp. 970–979. Association for Computational Linguistics (July 2011)
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: Proceedings of 5th International Joint Conference on Natural Language Processing, Chiang Mai, Thailand, pp. 309–317. Asian Federation of Natural Language Processing (November 2011)
Li, Z., Sun, M.: Punctuation as implicit annotations for Chinese word segmentation. Computational Linguistics 35(4), 505–512 (2009)
Spitkovsky, V.I., Jurafsky, D., Alshawi, H.: Profiting from mark-up: Hyper-text annotations for guided parsing. In: Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, Uppsala, Sweden, pp. 1278–1287. Association for Computational Linguistics (July 2010)
Zhang, K., Sun, M., Zhou, C.: Word segmentation on Chinese mirco-blog data with a linear-time incremental model. In: Proceedings of the Second CIPS-SIGHAN Joint Conference on Chinese Language Processing, Tianjin, China, pp. 41–46. Association for Computational Linguistics (December 2012)
Zhang, Y., Clark, S.: Chinese segmentation with a word-based perceptron algorithm, Prague, Czech Republic, pp. 840–847. Association for Computational Linguistics (June 2007)
Zhang, Y., Clark, S.: Syntactic processing using the generalized perceptron and beam search. Computational Linguistics (Early Access), 1–47 (2011)
Huang, L., Sagae, K.: Dynamic programming for linear-time incremental parsing. In: Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, Uppsala, Sweden, pp. 1077–1086. Association for Computational Linguistics (July 2010)
Duan, H., Sui, Z., Tian, Y., Li, W.: The cips-sighan clp 2012 Chinese word segmentation on microblog corpora bakeoff. In: Proceedings of the Second CIPS-SIGHAN Joint Conference on Chinese Language Processing, Tianjin, China, pp. 35–40. Association for Computational Linguistics (December 2012)
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)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zhang, K., Su, J., Zhou, C. (2013). Improving Chinese Word Segmentation Using Partially Annotated Sentences. In: Sun, M., Zhang, M., Lin, D., Wang, H. (eds) Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data. NLP-NABD CCL 2013 2013. Lecture Notes in Computer Science(), vol 8202. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-41491-6_1
Download citation
DOI: https://doi.org/10.1007/978-3-642-41491-6_1
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-41490-9
Online ISBN: 978-3-642-41491-6
eBook Packages: Computer ScienceComputer Science (R0)