Cooking recipes exist in abundance; but due to their unstructured text format, they are hard to study quantitatively beyond treating them as simple bags of words. In this paper, we proposed an ingredient-instruction dependency tree data structure to represent recipes. The proposed representation allows for more refined comparison of recipes and recipe-parts, and is a step towards semantic representation of recipes. Furthermore, we built a parser that maps recipes into the proposed representation. The parser’s edge prediction accuracy of 93.5% improved over a strong baseline of 85.7% (54.5% error reduction).
Publications
Jermsurawong, Jermsak and Nizar Habash. Predicting the structure of Cooking Recipes. In Proceedings of EMNLP, Lisbon, 2015.
Your journey to NYUAD starts here. Attend an application workshop or information session.Admissions Events
Live the possibilities. Be part of a dynamic community of students from over 115 countries.Take a Tour
