Diversity-Promoting GAN: A Cross-Entropy Based Generative Adversarial Network for Diversified Text Generation
Abstract
Existing text generation methods tend to produce repeated and ”boring” expressions. To tackle this problem, we propose a new text generation model, called Diversity-Promoting Generative Adversarial Network (DP-GAN). The proposed model assigns low reward for repeatedly generated text and high reward for ”novel” and fluent text, encouraging the generator to produce diverse and informative text. Moreover, we propose a novel language-model based discriminator, which can better distinguish novel text from repeated text without the saturation problem compared with existing classifier-based discriminators. The experimental results on review generation and dialogue generation tasks demonstrate that our model can generate substantially more diverse and informative text than existing baselines.- Anthology ID:
- D18-1428
- Volume:
- Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
- Month:
- October-November
- Year:
- 2018
- Address:
- Brussels, Belgium
- Editors:
- Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii
- Venue:
- EMNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3940–3949
- Language:
- URL:
- https://aclanthology.org/D18-1428
- DOI:
- 10.18653/v1/D18-1428
- Cite (ACL):
- Jingjing Xu, Xuancheng Ren, Junyang Lin, and Xu Sun. 2018. Diversity-Promoting GAN: A Cross-Entropy Based Generative Adversarial Network for Diversified Text Generation. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 3940–3949, Brussels, Belgium. Association for Computational Linguistics.
- Cite (Informal):
- Diversity-Promoting GAN: A Cross-Entropy Based Generative Adversarial Network for Diversified Text Generation (Xu et al., EMNLP 2018)
- PDF:
- https://preview.aclanthology.org/teach-a-man-to-fish/D18-1428.pdf