Exploiting Food Embeddings for Ingredient Substitution

Chantal Pellegrini, Ege Özsoy, Monika Wintergerst, Georg Groh

2021

Abstract

Identifying ingredient substitutes for cooking recipes can be beneficial for various goals, such as nutrient optimization or avoiding allergens. Natural language processing (NLP) techniques can be valuable tools to make use of the vast cooking-related knowledge available online, and aid in finding ingredient alternatives. Despite previous approaches to identify ingredient substitutes, there is still a lack of research in this area regarding the most recent developments in the field of NLP. On top of that, a lack of standardized evaluation metrics makes comparing approaches difficult. In this paper, we present two models for ingredient embeddings, Food2Vec and FoodBERT. In addition, we combine both approaches with images, resulting in two multimodal representation models. FoodBERT is furthermore used for relation extraction. We conduct a ground truth based evaluation for all approaches, as well as a human evaluation. The comparison shows that FoodBERT, and especially the multimodal version, is best suited for substitute recommendations in dietary use cases.

Paper Citation

in Harvard Style

Pellegrini C., Özsoy E., Wintergerst M. and Groh G. (2021). Exploiting Food Embeddings for Ingredient Substitution. In Proceedings of the 14th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2021) - Volume 5: HEALTHINF; ISBN 978-989-758-490-9, SciTePress, pages 67-77. DOI: 10.5220/0010202000670077

in Bibtex Style

@conference{healthinf21,
author={Chantal Pellegrini and Ege Özsoy and Monika Wintergerst and Georg Groh},
title={Exploiting Food Embeddings for Ingredient Substitution},
booktitle={Proceedings of the 14th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2021) - Volume 5: HEALTHINF},
year={2021},
pages={67-77},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010202000670077},
isbn={978-989-758-490-9},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2021) - Volume 5: HEALTHINF
TI - Exploiting Food Embeddings for Ingredient Substitution
SN - 978-989-758-490-9
AU - Pellegrini C.
AU - Özsoy E.
AU - Wintergerst M.
AU - Groh G.
PY - 2021
SP - 67
EP - 77
DO - 10.5220/0010202000670077
PB - SciTePress