Abstract
The classification of Chinese word semantic relations is a significant research topic in the field of natural language processing. Compared with studies which identify the relation of word-pairs in given texts, the task of context-free lexical relational classification is more challenging due to the lack of context. A common way of solving this problem is to use word embeddings and lexical features to train a classifier. In this paper, we design various combinations of deep learning models and features and propose a joint model based on convolutional neural network and highway network. The joint model has reached a f1 value of 0.58 and outperform all the other deep learning models now available. Furthermore, we design extensive experiments to analyze how the magnitude of the training data influences the model’s performance and whether the distribution of data influences model’s performance.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Girju, R., Nakov, P., Nastase, V., Szpakowicz, S., Turney, P., Yuret, D.: Classification of semantic relations between nominals. Lang. Resour. Eval. 43, 105–121 (2009)
Iris, H., Su, N.K., Zornitsa, K., Preslav, N., Diarmuid, Ó.S., Sebastian, P., Marco, P., Lorenza, R., Stan, S.: SemEval-2010 task 8: multi-way classification of semantic relations between pairs of nominals. In: Eneko, A., Lluis, M, Richard, W. (eds) Workshop on Semantic Evaluations: Recent Achievements and Future Directions, pp. 94–99. Association for Computational Linguistics, Stroudsburg, PA, USA (2009)
Vylomova, E., Rimell, L., Cohn, T., Baldwin, T.: Take and Took, Gaggle and Goose, Book and Read: Evaluating the Utility of Vector Differences for Lexical Relation Learning. Computer Science (2015)
Hashimoto, K., Stenetorp, P., Miwa, M., Tsuruoka, Y.: Task-oriented learning of word embeddings for semantic relation classification. Computer Science (2015)
Shi, J.E., Jia, S., Xiang, Y.: Study on the Chinese word semantic relation classification with word embedding. In: Huang, X., Jiang, J., Zhao, D., Feng, Y., Hong, Y. (eds.) Natural Language Processing and Chinese Computing. Lecture Notes in Computer Science, vol. 10619, pp. 849–855. Springer, Cham (2017)
Li, C., Ma, T.: Classification of Chinese word semantic relations. In: Huang, X., Jiang, J., Zhao, D., Feng, Y., Hong, Y. (eds.) Natural Language Processing and Chinese Computing. Lecture Notes in Computer Science, vol. 10619, pp. 465–473. Springer, Cham (2017)
Zhou, Y., Lan, M., Wu, Y.: Effective semantic relationship classification of context-free Chinese words with simple surface and embedding features. In: Huang, X., Jiang, J., Zhao, D., Feng, Y., Hong, Y. (eds) Natural Language Processing and Chinese Computing. Lecture Notes in Computer Science, vol. 10619, pp. 456–464. Springer, Cham (2017)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Pereira, F., Burges, C.J.C., Bottou, L., Weinberger, K.Q. (eds.) Neural Information Processing Systems, vol. 1, pp. 1097–1105. Curran Associates Inc., USA (2012)
Srivastava, R.K., Greff, K., Schmidhuber, J.: Training very deep networks. In: Cortes, C., Lee, D. D., Sugiyama, M., Garnett, R. (eds.) Neural Information Processing Systems, vol. 2, pp. 2377–2385. MIT Press, Cambridge (2012)
Sanchez, I., Riedel, S.: How well can we predict hypernyms from word embeddings? A dataset-centric analysis. EACL 2, 401–407 (2017)
Mikolov, T., Yih, W., Zweig, G.: Linguistic regularities in continuous space word representations. HLT-NAACL 13, 746–751 (2013)
He, H., Gimpel, K., Lin, J.J.: Multi-perspective sentence similarity modeling with convolutional neural networks. In: EMNLP, pp. 1576–1586 (2015)
Zeng, D., Liu, K., Chen, Y., Zhao, J.: Distant supervision for relation extraction via piecewise convolutional neural networks. In: EMNLP, pp. 1753–1762 (2015)
Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. Computer Science (2014)
Ackowledgement
This work is supported by the MOE (Ministry of Education in China) Project of Humanities and Social Sciences (Project No. 18YJA740030), and the Fundamental Research Funds for the Central Universities, and the Research Funds of Beijing Language and Culture University (Project No. 18YCX009).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Deng, Y., Lu, M., Li, H., Liu, P. (2018). A Deep Learning Baseline for the Classification of Chinese Word Semantic Relations. In: Hong, JF., Su, Q., Wu, JS. (eds) Chinese Lexical Semantics. CLSW 2018. Lecture Notes in Computer Science(), vol 11173. Springer, Cham. https://doi.org/10.1007/978-3-030-04015-4_55
Download citation
DOI: https://doi.org/10.1007/978-3-030-04015-4_55
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-04014-7
Online ISBN: 978-3-030-04015-4
eBook Packages: Computer ScienceComputer Science (R0)