no code implementations • IJCNLP 2017 • Atsushi Ushiku, Hayato Hashimoto, Atsushi Hashimoto, Shinsuke Mori
In this paper, we focus on procedure execution videos, in which a human makes or repairs something and propose a method for generating procedural texts from them.
no code implementations • LREC 2016 • Shinsuke Mori, John Richardson, Atsushi Ushiku, Tetsuro Sasada, Hirotaka Kameko, Yoshimasa Tsuruoka
We describe a detailed definition of named entities and show some statistics of our game commentary corpus.
no code implementations • LREC 2016 • Atsushi Ushiku, Tetsuro Sasada, Shinsuke Mori
In Japanese, the raw text parsing is divided into three steps: word segmentation, part-of-speech tagging, and dependency parsing.