Natural Language Processing

A lot of information in a recipe is in the form of text. Therefore, Natural Language Processing is very important for us at Cookpad. For example, recipe search, recipe classification, and recipe summarization developed by Cookpad embody the information retrieval, document classification, and automatic summarization that are all applications of Natural Language Processing. To realize these, it is necessary to develop basic technologies of Natural Language Processing such as morphological analysis, named entity recognition, and synonymous expression recognition for the recipe domain. In this way, the R&D department studies Natural Language Processing from both basic and applied aspects, and supports the development of the company’s mission of “Make Everyday Cooking Fun”.

Our Activity

A neat example of the magic of Machine Learning
27 Mar 2018
by EvanderD Details
Using Skip-Thought Vectors
16 Mar 2018
by Ammar Zaher Details


Visual Grounding Annotation of Recipe Flow Graph
Taichi Nishimura, Suzushi Tomori, Hayato Hashimoto, Atsushi Hashimoto, Yoko Yamakata, Jun Harashima, Yoshitaka Ushiku, and Shinsuke Mori
Proceedings of the 12th International Conference on Language Resources and Evaluation (LREC 2020)

Calorie Estimation in a Real-World Recipe Service
Jun Harashima, Makoto Hiramatsu, and Satoshi Sanjo
Proceedings of the 32nd Annual Conference on Innovative Applications of Artificial Intelligence (IAAI-20)

Named Entity Recognition by Character-based Word Classification using a Domain Specific Dictionary
Makoto Hiramatsu, Kei Wakabayashi, and Jun Harashima
Proceedings of the 20th International Conference on Computational Linguistics and Intelligent Text Processing (CICLing 2019)

Step or Not: Discriminator for The Real Instructions in User-generated Recipes
Shintaro Inuzuka, Takahiko Ito, and Jun Harashima
Proceedings of the 4th Workshop on Noisy User-generated Text (W-NUT 2018)

Two-Step Validation in Character-based Ingredient Normalization
Jun Harashima and Yoshiaki Yamada
Proceedings of the 10th Workshop on Multimedia for Cooking and Eating Activities (CEA 2018)

Design in Everyday Cooking: Challenges for Assisting with Menu Planning and Food Preparation
Atsushi Hashimoto, Jun Harashima, Yoko Yamakata, and Shinsuke Mori
Proceedings of the 8th International Conference on Cross-Cultural Design (CCD 2016)

A Large-Scale Recipe and Meal Data Collection as Infrastructure for Food Research
Jun Harashima, Michiaki Ariga, Kenta Murata, and Masayuki Ioki
Proceedings of the 10th International Conference on Language Resources and Evaluation (LREC 2016)

Japanese-English Machine Translation of Recipe Texts
Takayuki Sato, Jun Harashima, and Mamoru Komachi
Proceedings of the 3rd Workshop on Asian Translation (WAT 2016)