WETCAT - Web-Enabled Translation Using Corpus-Based Acquisition of Transfer Rules

In this paper, we present a Web interface to a Japanese-English rule-based machine translation system. One main feature of our translation system is that the transfer rules have not been designed by hand but are learnt automatically from a parallel corpus. The user can customize the rule base by simply correcting translation results. In addition, it is possible to display token lists, parse trees, and transfer rules, which makes our system also a very useful tool for language students. The system has been implemented in Amzi! Prolog, using the Amzi logic server CGI interface to develop the Web application