Abstract
Comparative sentences are common in human languages. In online comments, a comparative sentence usually contains the subjective attitude or emotional tendency of a reviewer. Hence, comparative elements extraction (CEE) is valuable for opinion mining and sentiment analysis. Most of the existing CEE systems use rule-based or machine learning approaches that need to construct a rule base or spend a huge amount of effort on feature engineering. These approaches usually involve multiple steps, and the performance of each step relies on the accuracy of the previous step, risking error cascading oversteps. In this paper, we adopt a neural network approach to CEE, which supports end-to-end training and automatic learning of sentence representation. Furthermore, considering the high relevance of CEE and comparative sentences recognition (CSR), we propose a multi-task learning model to combine the two tasks, which can further improve the performance of CEE. Experiment results show that both our neural network approach and multi-task learning are effective for CEE.
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 subscriptionsReferences
Ding, C.: A Course for Mandarin Chinese Grammar, pp. 81–95. Peking University Press, Beijing (2009)
Wang, S., Zhao, G., Liu, H.: Comparison element ellipsis identification based on rules and sequence patterns. J. Shanxi Univ. (Nat. Sci. Ed.) 38, 85–92 (2015)
Jindal, N., Bing, L.: Mining comparative sentences and relations. In: Proceedings of the 21st National Conference on Artificial Intelligence, pp. 1331–1336. AAAI Press, Menlo Park (2006)
Song, R., Lin, H., Chang, F.: Chinese comparative sentences identification and comparative relations extraction. J. Chin. Inf. Process. 23, 102–107 (2009)
Wang, W., Zhao, T., Xin, G., Xu, Y.: Extraction of comparative elements using conditional random fields. Acta Automatica Sinica 41, 1385–1393 (2015)
Jacob, D., Chang, M., Kenton, L., Kristina, T.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol. 1, pp. 4171–4186. ACL, Stroudsburg (2019)
Zhou, H., Hou, M., Hou, M., Teng, Y.: Chinese comparative sentences identification and comparative elements extraction based on semantic classification. J. Chin. Inf. Process. 28, 136–141 (2014)
Kessler, W., Kuhn, J.: Detection of product comparisons-how far does an out-of-the-box semantic role labeling system take you? In: Proceedings of the 2013 Conference on Empirical Methods on Natural Language Processing, pp. 1892–1897. ACL, Stroudsburg (2013)
Hou, F., Li, G.: Mining chinese comparative sentences by semantic role labeling. In: Proceedings of the 2008 International Conference on Machine Learning and Cybernetics, pp. 2563–2568. IEEE, Piscataway (2008)
Xing, L., Liu, L.: Chinese standard comparative sentence recognition and extraction research. In: Proceedings of the 2013 International Conference on Information Engineering and Applications, pp. 415−422. Springe, London (2013)
Huang, G., Yao, T., Liu, Q.: Mining Chinese comparative sentences and relations based on CRF algorithm. Appl. Res. Comput. 27, 2061–2064 (2010)
John, L., Andrew, M., Fernando, P.: Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: Proceedings of the 18th International Conference Machine Learning, pp. 282−289. ACM, New York (2001)
Bai, L., Hu, R., Liu, Z.: Recognition of comparative sentences based on syntactic and semantic rules-system. Acta Scientiarum Naturalium Universitatis Pekinensis 51, 275–281 (2015)
Zhang, C., Feng, C., Liu, Q., Shi, C., Huang, H., Zhou, H.: Chinese comparative sentence identification based on multi-feature fusion. J. Chin. Inf. Process. 27, 110–116 (2013)
Yoon, K.: Convolutional neural networks for sentence classification. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1746–1751. ACL, Stroudsburg (2014)
Liadh, K., et al.: Overview of the CLEF eHealth evaluation lab 2019. In: Experimental IR Meets Multilinguality, Multimodality, and Interaction. CLEF 2019. Lecture Notes in Computer Science, vol. 11696, pp. 322−339. Springer, Cham (2019)
Yu, J., Jiang, J.: Adapting BERT for target-oriented multimodal sentiment classification. In: Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, pp. 5408−5414. Morgan Kaufmann, San Francisco (2019)
Rich, A.C.: Multitask learning: a knowledge-based source of inductive bias. In: Proceedings of the Tenth International Conference Machine Learning, pp. 41−48. ACM, New York (1993)
Li, Q., Ji, H.: Incremental joint extraction of entity mentions and relations. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, vol. 1, pp. 402–412. ACL, Stroudsburg (2014)
Yuan, Z., David, W.: Stack-propagation: improved representation learning for syntax. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, vol. 1, pp. 1557–1566. ACL, Stroudsburg (2016)
Tomas, M., Ilya, S., Kai, C., Gregory, S.C., Jeffrey, D.: Distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems, NIPS 2013, vol. 26, pp. 3111–3119. MIT Press, Cambridge (2013)
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning internal representations by error propagation. In: Parallel distributed processing: explorations in the microstructure of cognition, vol. 1, pp. 318–362. ACM, New York (1986)
Acknowledgements
This research project is supported by the National Natural Science Foundation of China (61872402), the Humanities and Social Science Project of the Ministry of Education (17YJAZH068), Science Foundation of Beijing Language and Culture University (supported by ‘‘the Fundamental Research Funds for the Central Universities’’) (18ZDJ03), the Open Project Program of the National Laboratory of Pattern Recognition (NLPR), the Fundamental Research Funds for the Central Universities, and Research Funds of Beijing Language and Culture University (20YCX147).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Liu, D., Wang, L., Shao, Y. (2021). Multi-task Learning Neural Networks for Comparative Elements Extraction. 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_33
Download citation
DOI: https://doi.org/10.1007/978-3-030-81197-6_33
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)