Multiple Text Style Transfer by using Word-level Conditional Generative Adversarial Network with Two-Phase Training

Chih-Te Lai, Yi-Te Hong, Hong-You Chen, Chi-Jen Lu, Shou-De Lin


Abstract
The objective of non-parallel text style transfer, or controllable text generation, is to alter specific attributes (e.g. sentiment, mood, tense, politeness, etc) of a given text while preserving its remaining attributes and content. Generative adversarial network (GAN) is a popular model to ensure the transferred sentences are realistic and have the desired target styles. However, training GAN often suffers from mode collapse problem, which causes that the transferred text is little related to the original text. In this paper, we propose a new GAN model with a word-level conditional architecture and a two-phase training procedure. By using a style-related condition architecture before generating a word, our model is able to maintain style-unrelated words while changing the others. By separating the training procedure into reconstruction and transfer phases, our model is able to learn a proper text generation process, which further improves the content preservation. We test our model on polarity sentiment transfer and multiple-attribute transfer tasks. The empirical results show that our model achieves comparable evaluation scores in both transfer accuracy and fluency but significantly outperforms other state-of-the-art models in content compatibility on three real-world datasets.
Anthology ID:
D19-1366
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
3579–3584
Language:
URL:
https://aclanthology.org/D19-1366
DOI:
10.18653/v1/D19-1366
Bibkey:
Cite (ACL):
Chih-Te Lai, Yi-Te Hong, Hong-You Chen, Chi-Jen Lu, and Shou-De Lin. 2019. Multiple Text Style Transfer by using Word-level Conditional Generative Adversarial Network with Two-Phase Training. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 3579–3584, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Multiple Text Style Transfer by using Word-level Conditional Generative Adversarial Network with Two-Phase Training (Lai et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-1366.pdf
Attachment:
 D19-1366.Attachment.zip