Abstract
Text sentiment transfer models modify sentence sentiments while retaining their semantic content. The main challenge is to separate sentiment-independent content information from the semantic information of the sentence. The previous works usually expect to utilize the model encoder to infer the sentence-level representation that removed sentiment information. However, the strength of the models’ abilities to reconstruct text is difficult to control which resulting encoder infer sentence-level sentiment-independent content embedding failed. In this paper, we address this challenge by using word-level representation. We first use the POS-Tagging technique to tag the part of speech of word sequence, then extracting content keywords by three schemes and use them as input, rather than the entire sentence, to obtain a purer word-level sentiment-independent content representation. In this way, the model does not require to infer the sentiment-independent representation, which avoids the instability of the adversarial training process. Experiments show that our method achieves the state-of-the-art performance and is also effective in long text sentiment transfer tasks.
Supported by China National Social Science Fund (19BXW110).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate (2014). arXiv:1409.0473v7
Wen, T.H., Vandyke, D., Mrksic, N., et al.: A network-based end-to-end trainable task-oriented dialogue system. In: Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics, pp. 438–449. EACL, Valencia (2017)
Fu, Z., Tan, X., Peng, N., et al.: Style transfer in text: exploration and evaluation. In: Thirty-Second AAAI Conference on Artificial Intelligence, pp. 663-670. AAAI, San Francisco (2018)
Hu, Z., Yang, Z., Liang, X., et al.: Toward controlled generation of text. In: Proceedings of the 34th International Conference on Machine Learning, pp. 1587–1596. PMLR, Sydney (2017)
Shen, T., Lei, T., Barzilay, R., et al.: Style transfer from non-parallel text by cross-alignment. In: Proceedings of 31st Conference on Neural Information Processing Systems, pp. 6830–6841. NeurIPS, Long Beach (2017)
Yang, Z., Hu, Z., Dyer, C., Berg-Kirkpatrick, T., et al.: Unsupervised text style transfer using language models as discriminators. In: Proceedings of 32st Conference on Neural Information Processing Systems, pp. 7298–7309. NeurIPS, Montr é al (2018)
Xu, J., Sun, X., Zeng, Q., et al.: Unpaired sentiment-to-sentiment translation: a cycled reinforcement learning approach. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, pp. 979–988. ACL, Melbourne (2018)
John, V., Mou, L., Bahuleyan, H., et al.: Disentangled representation learning for text style transfer. In: Proceedings of the 57th Conference of the Association for Computational Linguistics, pp. 424–434. ACL, Florence (2019)
Zhao, Y., Bi, W., Cai, D., et al.: Language style transfer from sentences with arbitrary unknown styles (2018). arXiv preprint arXiv:1808.04071
Gong, H., Bhat, S., Wu, L., et al.: Reinforcement learning based text style transfer without parallel training corpus. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics, pp. 3168–3180. NAACL-HLT, Minneapolis (2019)
Prabhumoye, S., Tsvetkov, Y., Salakhutdinov, R., et al.: Style transfer through back-translation. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Long Papers), pp. 866–876. ACL, Melbourne (2018)
Yu, L., Zhang, W., Wang, J., et al.: Seqgan: sequence generative adversarial nets with policy gradient. In: Proceedings of the Thirty-First Conference on Artificial Intelligence, pp. 2852–2858. AAAI, San Francisco (2017)
Luo, F., Li, P., Yang, P., et al.: Towards fine-grained text sentiment transfer. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 2013–2022 (2019)
Li, J., Jia, R., He, H., et al.: Delete, retrieve, generate: a simple approach to sentiment and style transfer. In: Proceedings of the 16th Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 1865–1874. NAACL, New Orleans (2018)
Lample, G., Subramanian, S., Smith, E., et al.: Multiple-attribute text rewriting. In: ICLR (Poster) (2019)
Liao, Y., Bing, L., Li, P., et al.: Quase: sequence editing under quantifiable guidance. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 3855–3864 (2018)
Hu, M., Liu, B.: Mining and summarizing customer reviews. In: Proceedings of the Tenth International Conference on Knowledge Discovery and Data Mining, pp. 168–177. SIGKDD, Seattle (2004)
McAuley, J.J., Leskovec, J.: From amateurs to connoisseurs: modeling the evolution of user expertise through online reviews. In Proceedings of the 22nd International Conference on World Wide Web, pp. 897–908. WWW, Rio de Janeiro (2013)
Kim, Y.: Convolutional neural networks for sentence classification. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, pp. 1746–1751. EMNLP, Doha (2014)
Mir, R., Felbo, B., Obradovich, N., et al.: Evaluating style transfer for text. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 495–504. NAACL-HLT, Minneapolis (2019)
Hu, Z., Shi, H., Yang, Z., et al.: Texar: a modularized, versatile, and extensible toolkit for text generation. In: Proceedings of the 57th Conference of the Association for Computational Linguistics, pp. 159–164. ACL, Florence (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Hu, S., Li, B., Lin, K., Wang, R., Liu, K. (2020). Text Sentiment Transfer Methods by Using Sentence Keywords. In: Fujita, H., Fournier-Viger, P., Ali, M., Sasaki, J. (eds) Trends in Artificial Intelligence Theory and Applications. Artificial Intelligence Practices. IEA/AIE 2020. Lecture Notes in Computer Science(), vol 12144. Springer, Cham. https://doi.org/10.1007/978-3-030-55789-8_4
Download citation
DOI: https://doi.org/10.1007/978-3-030-55789-8_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-55788-1
Online ISBN: 978-3-030-55789-8
eBook Packages: Computer ScienceComputer Science (R0)