Abstract
Recent pre-trained language models have shown promising capability to generate fluent and realistic natural text. However, generating multi-sentence text with global content planning has been a long-existing research question. The current controlled text generation models cannot directly address this issue, as they usually condition on single known control attribute. We propose a low-cost yet effective framework that explicitly models content plans and optimizes the joint distribution of the natural sequence and the content plans in a plug-and-play post-processing manner. We evaluate our model with extensive automatic metrics and human evaluations and show that it achieves the state-of-the-art performance on the recipe generation task on Recipe1M+ dataset.- Anthology ID:
- 2022.gem-1.19
- Volume:
- Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM)
- Month:
- December
- Year:
- 2022
- Address:
- Abu Dhabi, United Arab Emirates (Hybrid)
- Editors:
- Antoine Bosselut, Khyathi Chandu, Kaustubh Dhole, Varun Gangal, Sebastian Gehrmann, Yacine Jernite, Jekaterina Novikova, Laura Perez-Beltrachini
- Venue:
- GEM
- SIG:
- SIGGEN
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 223–234
- Language:
- URL:
- https://aclanthology.org/2022.gem-1.19
- DOI:
- 10.18653/v1/2022.gem-1.19
- Cite (ACL):
- Yinhong Liu, Yixuan Su, Ehsan Shareghi, and Nigel Collier. 2022. Plug-and-Play Recipe Generation with Content Planning. In Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM), pages 223–234, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.
- Cite (Informal):
- Plug-and-Play Recipe Generation with Content Planning (Liu et al., GEM 2022)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2022.gem-1.19.pdf