Plug-and-play recipe generation with content planning

Yinhong Liu, Yixuan Su, Ehsan Shareghi, Nigel Collier

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearch

1 Citation (Scopus)


Recent pre-trained language models have shown promising capabilities in generating fluent and realistic natural language text. However, generating multi-sentence text with global content planning has been a long-existing research question. Current approaches for controlled text generation can hardly address this issue, as they usually condition on single known control attributes. In this study, we propose a low-cost yet effective framework which explicitly models the global content plan of the generated text. Specifically, it optimizes the joint distribution of the natural language sequence and the global content plan in a plug- and-play manner. We conduct extensive experiments on the well-established Recipe1M+ benchmark. Both automatic and human evaluations verify that our model achieves the state-of-the-art performance on the task of recipe generation.

Original languageEnglish
Title of host publicationGEM 2022 - 2nd Workshop on Natural Language Generation, Evaluation, and Metrics, Proceedings of the Workshop
EditorsAntoine Bosselut, Khyathi Chandu, Kaustubh Dhole, Varun Gangal, Sebastian Gehrmann, Yacine Jernite, Jekaterina Novikova, Laura Perez-Beltrachini
Place of PublicationStroudsburg PA USA
PublisherAssociation for Computational Linguistics (ACL)
Number of pages12
ISBN (Electronic)9781959429128
Publication statusPublished - 2022
EventWorkshop on Natural Language Generation, Evaluation, and Metrics 2022 - Abu Dhabi, United Arab Emirates
Duration: 7 Dec 20227 Dec 2022
Conference number: 2nd (Proceedings) (Website)


ConferenceWorkshop on Natural Language Generation, Evaluation, and Metrics 2022
Abbreviated titleGEM 2022
Country/TerritoryUnited Arab Emirates
CityAbu Dhabi
Internet address

Cite this