Improvement of Translation Quality of English Newspaper Headlines by Automatic Pre-editing

Since the headlines of English news articles have a characteristicstyle, different from the styles which prevail in ordinary sentences, it is difficult for MT systems to generate high-quality translation for headlines.We try to solve this problem by adding to an existing system apre-editing module which rewrites headlines as ordinary expressions.Rewriting of headlines makes it possible to generate better translations which would not otherwise be generated, with little or no changes to the existing parts of the system. Focusing on the absence of a form of the verb be as a missing part of normal English, we have described rewriting rules for putting properly the verb be into headlines, based on information obtained by morpho-lexical and rough syntactic analysis.We have incorporated the proposed method into our English–JapaneseMT system, and carried out an experiment with 312 headlines as unknown data. Our method has satisfactorily marked 81.2% recall and 92.0% precision.