Abstract
Subject (In this paper, subject means “
/zhu ti” in Chinese, while we use “grammatical subject” to denote traditional “
/zhu yu” in Chinese.) recognition plays a significant role in the conversation with a Chatbot. The misclassification of the subject of a sentence leads to the misjudgment of the intention recognition. In this paper, we build a new dataset for subject recognition and propose several systems based on pre-trained language models. We first design annotation guidelines for human-chatbot conversational data, and hire annotators to build a new dataset according to the guidelines. Then, classification methods based on deep neural network are proposed. Finally, extensive experiments are conducted to testify the performance of different algorithms. The results show that our method achieves 88.5% \(F_1\) in the task of subject recognition. We also compare our systems with three other Chatbot systems and find ours perform the best.
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
Notes
- 1.
The term limited refers to specific reference and definite quantity, while non-limited means those generic reference and non-definite quantity. The subject discussed in this paper belongs to the limited, so the non-limited people are usually not regarded as subjects, such as the “men” in “All men must die”.
- 2.
- 3.
A subject-verb relation in LTP. https://github.com/HIT-SCIR/ltp.
- 4.
- 5.
References
Christensen, J., Soderland, S., Etzioni, O., et al.: An analysis of open information extraction based on semantic role labeling. In: K-CAP, pp. 113–120. ACM (2011)
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)
Joulin, A., Grave, E., Bojanowski, P., Mikolov, T.: Bag of tricks for efficient text classification. arXiv preprint arXiv:1607.01759 (2016)
Kim, S.M., Hovy, E.: Identifying opinion holders for question answering in opinion texts. In: AAAI 2005 Workshop, pp. 1367–1373 (2005)
Kim, Y.: Convolutional neural networks for sentence classification. arXiv preprint arXiv:1408.5882 (2014)
Lai, S., Xu, L., Liu, K., Zhao, J.: Recurrent convolutional neural networks for text classification. In: AAAI (2015)
Li, F., et al.: Structure-aware review mining and summarization. In: COLING, pp. 653–661 (2010)
Miyato, T., Dai, A.M., Goodfellow, I.: Adversarial training methods for semi-supervised text classification. arXiv preprint arXiv:1605.07725 (2016)
Peters, M.E., et al.: Deep contextualized word representations. arXiv preprint arXiv:1802.05365 (2018)
Punyakanok, V., Roth, D., Yih, W.t.: The importance of syntactic parsing and inference in semantic role labeling. Comput. Linguist. 34(2), 257–287 (2008)
Qi, H., Yang, M., Meng, Y., Han, X., Zhao, T.: Skeleton parsing for specific domain Chinese text. J. Chin. Inf. Process. 18(1), 1–5 (2004). (in Chinese)
Qiu, G., Liu, B., Bu, J., Chen, C.: Opinion word expansion and target extraction through double propagation. Comput. Linguist. 37(1), 9–27 (2011)
Rusu, D., Dali, L., Fortuna, B., Grobelnik, M., Mladenic, D.: Triplet extraction from sentences. In: IMSCI, pp. 8–12 (2007)
Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998–6008 (2017)
Wang, R., Ju, J., Li, S., Zhou, G.: Feature engineering for CRFs based opinion target extraction. J. Chin. Inf. Process. 26(2), 56–61 (2012). (in Chinese)
Wiegand, M., Klakow, D.: Convolution kernels for opinion holder extraction. In: NAACL-HLT, pp. 795–803 (2010)
Zhou, H., Huang, M., Zhang, T., Zhu, X., Liu, B.: Emotional chatting machine: emotional conversation generation with internal and external memory. In: AAAI (2018)
Zhou, P., et al.: Attention-based bidirectional long short-term memory networks for relation classification. In: ACL (2016)
Acknowledgements
The authors are supported by the National Natural Science Foundation of China (Grant No. 61603240). Corresponding author is Hao Shao. We also thank the anonymous reviewers for their insightful comments.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Li, F., Wei, H., Hao, Q., Zeng, R., Shao, H., Chen, W. (2019). Subject Recognition in Chinese Sentences for Chatbots. In: Tang, J., Kan, MY., Zhao, D., Li, S., Zan, H. (eds) Natural Language Processing and Chinese Computing. NLPCC 2019. Lecture Notes in Computer Science(), vol 11839. Springer, Cham. https://doi.org/10.1007/978-3-030-32236-6_46
Download citation
DOI: https://doi.org/10.1007/978-3-030-32236-6_46
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-32235-9
Online ISBN: 978-3-030-32236-6
eBook Packages: Computer ScienceComputer Science (R0)
