Counterfactual Recipe Generation: Exploring Compositional Generalization in a Realistic Scenario

Xiao Liu, Yansong Feng, Jizhi Tang, Chengang Hu, Dongyan Zhao


Abstract
People can acquire knowledge in an unsupervised manner by reading, and compose the knowledge to make novel combinations. In this paper, we investigate whether pretrained language models can perform compositional generalization in a realistic setting: recipe generation. We design the counterfactual recipe generation task, which asks models to modify a base recipe according to the change of an ingredient. This task requires compositional generalization at two levels: the surface level of incorporating the new ingredient into the base recipe, and the deeper level of adjusting actions related to the changing ingredient. We collect a large-scale recipe dataset in Chinese for models to learn culinary knowledge, and a subset of action-level fine-grained annotations for evaluation.We finetune pretrained language models on the recipe corpus, and use unsupervised counterfactual generation methods to generate modified recipes.Results show that existing models have difficulties in modifying the ingredients while preserving the original text style, and often miss actions that need to be adjusted. Although pretrained language models can generate fluent recipe texts, they fail to truly learn and use the culinary knowledge in a compositional way. Code and data are available at https://github.com/xxxiaol/counterfactual-recipe-generation.
Anthology ID:
2022.emnlp-main.497
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7354–7370
Language:
URL:
https://aclanthology.org/2022.emnlp-main.497
DOI:
10.18653/v1/2022.emnlp-main.497
Bibkey:
Cite (ACL):
Xiao Liu, Yansong Feng, Jizhi Tang, Chengang Hu, and Dongyan Zhao. 2022. Counterfactual Recipe Generation: Exploring Compositional Generalization in a Realistic Scenario. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 7354–7370, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Counterfactual Recipe Generation: Exploring Compositional Generalization in a Realistic Scenario (Liu et al., EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.497.pdf