English

A neural network system for transformation of regional cuisine style

Computers and Society 2018-06-26 v2 Computation and Language

Abstract

We propose a novel system which can transform a recipe into any selected regional style (e.g., Japanese, Mediterranean, or Italian). This system has two characteristics. First the system can identify the degree of regional cuisine style mixture of any selected recipe and visualize such regional cuisine style mixtures using barycentric Newton diagrams. Second, the system can suggest ingredient substitutions through an extended word2vec model, such that a recipe becomes more authentic for any selected regional cuisine style. Drawing on a large number of recipes from Yummly, an example shows how the proposed system can transform a traditional Japanese recipe, Sukiyaki, into French style.

Keywords

Cite

@article{arxiv.1705.03487,
  title  = {A neural network system for transformation of regional cuisine style},
  author = {Masahiro Kazama and Minami Sugimoto and Chizuru Hosokawa and Keisuke Matsushima and Lav R. Varshney and Yoshiki Ishikawa},
  journal= {arXiv preprint arXiv:1705.03487},
  year   = {2018}
}