Discriminative Method for Japanese Kana-Kanji Input Method
Hiroyuki Tokunaga, Daisuke Okanohara, Shinsuke Mori · 2011
The most popular type of input method in Japan is kana-kanji conversion, conver-sion from a string of kana to a mixed kanji-kana string. However there is no study using discrim-inative methods like structured SVMs for kana-kanji conversion. One of the reasons is that learning a discriminative model from a large data set is often intractable. However, due to progress of recent re-searches, large scale learning of discrim-inative models become feasible in these days. In the present paper, we investigate whether discriminative methods such as structured SVMs can improve the accu-racy of kana-kanji conversion. To the best of our knowledge, this is the first study comparing a generative model and a dis-criminative model for kana-kanji conver-sion. An experiment revealed that a dis-criminative method can improve the per-formance by approximately 3%. 1