What does it take to bake a cake? The RecipeRef corpus and anaphora resolution in procedural text

Published:

Biaoyan Fang, Timothy Baldwin and Karin Verspoor (2022) What does it take to bake a cake? The RecipeRef corpus and anaphora resolution in procedural text. In Findings of ACL 2022, Dublin, Ireland.

@inproceedings{fang-etal-2022-take,
    title = "What does it take to bake a cake? The {R}ecipe{R}ef corpus and anaphora resolution in procedural text",
    author = "Fang, Biaoyan  and
      Baldwin, Timothy  and
      Verspoor, Karin",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2022",
    month = may,
    year = "2022",
    address = "Dublin, Ireland",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.findings-acl.275",
    doi = "10.18653/v1/2022.findings-acl.275",
    pages = "3481--3495",
    abstract = "Procedural text contains rich anaphoric phenomena, yet has not received much attention in NLP. To fill this gap, we investigate the textual properties of two types of procedural text, recipes and chemical patents, and generalize an anaphora annotation framework developed for the chemical domain for modeling anaphoric phenomena in recipes. We apply this framework to annotate the RecipeRef corpus with both bridging and coreference relations. Through comparison to chemical patents, we show the complexity of anaphora resolution in recipes. We demonstrate empirically that transfer learning from the chemical domain improves resolution of anaphora in recipes, suggesting transferability of general procedural knowledge.",
}

Abstract

Procedural text contains rich anaphoric phenomena, yet has not received much attention in NLP. To fill this gap, we investigate the textual properties of two types of procedural text, recipes and chemical patents, and generalize an anaphora annotation framework developed for the chemical domain for modeling anaphoric phenomena in recipes. We apply this framework to annotate the RecipeRef corpus with both bridging and coreference relations. Through comparison to chemical patents, we show the complexity of anaphora resolution in recipes. We demonstrate empirically that transfer learning from the chemical domain improves resolution of anaphora in recipes, suggesting transferability of general procedural knowledge.