[4Pin1] インタラクティブ(2)

[4Pin1-25] Neural Machine Translation with Kanji Decomposition

〇Vishu Gupta¹, Akihiro Nakamura¹, Haruki Fukuda¹, Takashi Tsunakawa¹, Yoshinobu Kano¹, Masafumi Nishida¹, Masafumi Nishimura¹ (1. Shizuoka University)

Keywords:Neural Machine Translation, Kanji Decomposition

This paper proposes a method for neural machine translation (NMT) with kanji decomposition of Japanese text. NMT models have restrictions of the vocabulary size, which can be solved by applying subword, character-level, or byte-based models. In Japanese text, the vocabulary size would not be minimized even in a character level because of kanji varieties. We report an experimental result of NMT model using Japanese text with kanji decomposition that is expected to satisfy both of decreasing vocabulary size and keeping kanji information.