CoCGAN: Contrastive Learning for Adversarial Category Text Generation
Xin Sheng, Linli Xu, Yinlong Xu, Changcun Bao, Huang Chen, Bo Ren
Abstract
The task of generating texts of different categories has attracted more and more attention in the area of natural language generation recently. Meanwhile, generative adversarial net (GAN) has demonstrated its effectiveness on text generation, and is further applied to category text generation in later works. Different from existing methods, which mainly consider the pairwise relations between the text embedding and the corresponding fixed one-hot class label (data-to-class relations), this paper proposes a novel Contrastive Category Generative Adversarial Net (CoCGAN) to incorporate contrastive learning into adversarial category text generation, considering more flexible data-to-class relations as well as relations between the multiple text embeddings in the same batch (data-to-data relations). The discriminator of CoCGAN discriminates the authenticity of given samples and optimizes a contrastive learning objective to capture both more flexible data-to-class relations and data-to-data relations among training samples. Accordingly, the generator tries to produce more realistic samples which can confuse the discriminator. Experimental results on both synthetic and real category text generation datasets demonstrate that CoCGAN can achieve significant improvements over the baseline category text generation models.- Anthology ID:
- 2022.coling-1.557
- Volume:
- Proceedings of the 29th International Conference on Computational Linguistics
- Month:
- October
- Year:
- 2022
- Address:
- Gyeongju, Republic of Korea
- Editors:
- Nicoletta Calzolari, Chu-Ren Huang, Hansaem Kim, James Pustejovsky, Leo Wanner, Key-Sun Choi, Pum-Mo Ryu, Hsin-Hsi Chen, Lucia Donatelli, Heng Ji, Sadao Kurohashi, Patrizia Paggio, Nianwen Xue, Seokhwan Kim, Younggyun Hahm, Zhong He, Tony Kyungil Lee, Enrico Santus, Francis Bond, Seung-Hoon Na
- Venue:
- COLING
- SIG:
- Publisher:
- International Committee on Computational Linguistics
- Note:
- Pages:
- 6403–6414
- Language:
- URL:
- https://aclanthology.org/2022.coling-1.557
- DOI:
- Cite (ACL):
- Xin Sheng, Linli Xu, Yinlong Xu, Changcun Bao, Huang Chen, and Bo Ren. 2022. CoCGAN: Contrastive Learning for Adversarial Category Text Generation. In Proceedings of the 29th International Conference on Computational Linguistics, pages 6403–6414, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
- Cite (Informal):
- CoCGAN: Contrastive Learning for Adversarial Category Text Generation (Sheng et al., COLING 2022)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2022.coling-1.557.pdf