RecipeBowl: A Cooking Recommender for Ingredients and Recipes Using Set Transformer

Keonwoo Kim; Donghyeon Park; Michael Spranger; Kana Maruyama; Jaewoo Kang

doi:10.1109/ACCESS.2021.3120265

RecipeBowl: A Cooking Recommender for Ingredients and Recipes Using Set Transformer

Keonwoo Kim, Donghyeon Park, Michael Spranger, Kana Maruyama, Jaewoo Kang

Research output: Contribution to journal › Article › peer-review

11 Citations (Scopus)

Abstract

Countless possibilities of recipe combinations challenge us to determine which additional ingredient goes well with others. In this work, we propose RecipeBowl which is a cooking recommendation system that takes a set of ingredients and cooking tags as input and suggests possible ingredient and recipe choices. We formulate a recipe completion task to train RecipeBowl on our constructed dataset where the model predicts a target ingredient previously eliminated from the original recipe. The RecipeBowl consists of a set encoder and a 2-way decoder for prediction. For the set encoder, we utilize the Set Transformer that builds meaningful set representations. Overall, our model builds a set representation of an leave-one-out recipe and maps it to the ingredient and recipe embedding space. Experimental results demonstrate the effectiveness of our approach. Furthermore, analysis on model predictions and interpretations show interesting insights related to cooking knowledge.

Original language	English
Pages (from-to)	143623-143633
Number of pages	11
Journal	IEEE Access
Volume	9
DOIs	https://doi.org/10.1109/ACCESS.2021.3120265
Publication status	Published - 2021
Externally published	Yes

Bibliographical note

Funding Information:
This research was supported by the National Research Foundation of Korea (No. NRF-2020R1A2C3010638), the MSIT(Ministry of Science and ICT), Korea, under the ICT Creative Consilience program(IITP-2021-2020-0-01819) supervised by the IITP(Institute for Information & communications Technology Planning & Evaluation) and SONY AI (https://ai.sony).

Publisher Copyright:
© 2013 IEEE.

Keywords

Food ingredient combination
food ingredient recommendation
food ingredient relations
recipe context learning
recipe recommendation
set representation learning

ASJC Scopus subject areas

General Computer Science
General Materials Science
General Engineering

Access to Document

10.1109/ACCESS.2021.3120265

Cite this

@article{6f25046d702342ae9dbd1dc92b926130,

title = "RecipeBowl: A Cooking Recommender for Ingredients and Recipes Using Set Transformer",

abstract = "Countless possibilities of recipe combinations challenge us to determine which additional ingredient goes well with others. In this work, we propose RecipeBowl which is a cooking recommendation system that takes a set of ingredients and cooking tags as input and suggests possible ingredient and recipe choices. We formulate a recipe completion task to train RecipeBowl on our constructed dataset where the model predicts a target ingredient previously eliminated from the original recipe. The RecipeBowl consists of a set encoder and a 2-way decoder for prediction. For the set encoder, we utilize the Set Transformer that builds meaningful set representations. Overall, our model builds a set representation of an leave-one-out recipe and maps it to the ingredient and recipe embedding space. Experimental results demonstrate the effectiveness of our approach. Furthermore, analysis on model predictions and interpretations show interesting insights related to cooking knowledge.",

keywords = "Food ingredient combination, food ingredient recommendation, food ingredient relations, recipe context learning, recipe recommendation, set representation learning",

author = "Keonwoo Kim and Donghyeon Park and Michael Spranger and Kana Maruyama and Jaewoo Kang",

note = "Funding Information: This research was supported by the National Research Foundation of Korea (No. NRF-2020R1A2C3010638), the MSIT(Ministry of Science and ICT), Korea, under the ICT Creative Consilience program(IITP-2021-2020-0-01819) supervised by the IITP(Institute for Information & communications Technology Planning & Evaluation) and SONY AI (https://ai.sony). Publisher Copyright: {\textcopyright} 2013 IEEE.",

year = "2021",

doi = "10.1109/ACCESS.2021.3120265",

language = "English",

volume = "9",

pages = "143623--143633",

journal = "IEEE Access",

issn = "2169-3536",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - RecipeBowl

T2 - A Cooking Recommender for Ingredients and Recipes Using Set Transformer

AU - Kim, Keonwoo

AU - Park, Donghyeon

AU - Spranger, Michael

AU - Maruyama, Kana

AU - Kang, Jaewoo

N1 - Funding Information: This research was supported by the National Research Foundation of Korea (No. NRF-2020R1A2C3010638), the MSIT(Ministry of Science and ICT), Korea, under the ICT Creative Consilience program(IITP-2021-2020-0-01819) supervised by the IITP(Institute for Information & communications Technology Planning & Evaluation) and SONY AI (https://ai.sony). Publisher Copyright: © 2013 IEEE.

PY - 2021

Y1 - 2021

N2 - Countless possibilities of recipe combinations challenge us to determine which additional ingredient goes well with others. In this work, we propose RecipeBowl which is a cooking recommendation system that takes a set of ingredients and cooking tags as input and suggests possible ingredient and recipe choices. We formulate a recipe completion task to train RecipeBowl on our constructed dataset where the model predicts a target ingredient previously eliminated from the original recipe. The RecipeBowl consists of a set encoder and a 2-way decoder for prediction. For the set encoder, we utilize the Set Transformer that builds meaningful set representations. Overall, our model builds a set representation of an leave-one-out recipe and maps it to the ingredient and recipe embedding space. Experimental results demonstrate the effectiveness of our approach. Furthermore, analysis on model predictions and interpretations show interesting insights related to cooking knowledge.

AB - Countless possibilities of recipe combinations challenge us to determine which additional ingredient goes well with others. In this work, we propose RecipeBowl which is a cooking recommendation system that takes a set of ingredients and cooking tags as input and suggests possible ingredient and recipe choices. We formulate a recipe completion task to train RecipeBowl on our constructed dataset where the model predicts a target ingredient previously eliminated from the original recipe. The RecipeBowl consists of a set encoder and a 2-way decoder for prediction. For the set encoder, we utilize the Set Transformer that builds meaningful set representations. Overall, our model builds a set representation of an leave-one-out recipe and maps it to the ingredient and recipe embedding space. Experimental results demonstrate the effectiveness of our approach. Furthermore, analysis on model predictions and interpretations show interesting insights related to cooking knowledge.

KW - Food ingredient combination

KW - food ingredient recommendation

KW - food ingredient relations

KW - recipe context learning

KW - recipe recommendation

KW - set representation learning

UR - http://www.scopus.com/inward/record.url?scp=85117826520&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2021.3120265

DO - 10.1109/ACCESS.2021.3120265

M3 - Article

AN - SCOPUS:85117826520

SN - 2169-3536

VL - 9

SP - 143623

EP - 143633

JO - IEEE Access

JF - IEEE Access

ER -

RecipeBowl: A Cooking Recommender for Ingredients and Recipes Using Set Transformer

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this