Abstract
Likelihood training and maximization-based decoding result in dull and repetitive generated texts even when using powerful language models (Holtzman et al., 2019). Adding a loss function for regularization was shown to improve text generation output by helping avoid unwanted properties, such as contradiction or repetition (Li at al., 2020). In this work, we propose fine-tuning a language model by using policy gradient reinforcement learning, directly optimizing for better generation. We apply this approach to minimizing repetition in generated text, and show that, when combined with unlikelihood training (Welleck et al., 2020), our method further reduces repetition without impacting the language model quality. We also evaluate other methods for improving generation at training and decoding time, and compare them using various metrics aimed at control for better text generation output.- Anthology ID:
- 2021.eacl-main.123
- Volume:
- Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
- Month:
- April
- Year:
- 2021
- Address:
- Online
- Editors:
- Paola Merlo, Jorg Tiedemann, Reut Tsarfaty
- Venue:
- EACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1432–1441
- Language:
- URL:
- https://aclanthology.org/2021.eacl-main.123
- DOI:
- 10.18653/v1/2021.eacl-main.123
- Cite (ACL):
- Evgeny Lagutin, Daniil Gavrilov, and Pavel Kalaidin. 2021. Implicit Unlikelihood Training: Improving Neural Text Generation with Reinforcement Learning. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 1432–1441, Online. Association for Computational Linguistics.
- Cite (Informal):
- Implicit Unlikelihood Training: Improving Neural Text Generation with Reinforcement Learning (Lagutin et al., EACL 2021)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2021.eacl-main.123.pdf
- Code
- vklabmipt/implicit-unlikelihood-training