Two methods for learning ALT-J/E translation rules from examples and a semantic hierarchy
Hussein Almuallim, Yasuhiro Akiba, Takefumi Yamazaki, Akio Yokoo, Shigeo Kaneda · 1994
This paper presents our work towards the automatic acquisition of translation rules from Japanese-English translation examples for NTT's ALT-J/E machine translation system. We apply two machine learning algorithms: Haussler's algorithm for learning internal disjunctive concept and Quinlan's ID3 algorithm. Experimental results show that our approach yields rules that are highly accurate compared to the manually created rules.