Patent Claim Translation based on Sublanguage-specific Sentence Structure

Abstract

Patent claim sentences, despite their legal importance in patent documents, still pose difficulties for state-of-the-art statistical machine translation (SMT) systems owing to their extreme lengths and their special sentence structure. This paper describes a method for improving the translation quality of claim sentences, by taking into account the features specific to the claim sublanguage. Our method overcomes the issue of special sentence structure, by transferring the sublanguage-specific sentence structure (SSSS) from the source language to the target language, using a set of synchronous context-free grammar rules. Our method also overcomes the issue of extreme lengths by taking the sentence components to be the processing unit for SMT. The results of an experiment demonstrate that our SSSS transfer method, used in conjunction with pre-ordering, significantly improves the translation quality in terms of BLEU scores by five points, in both English-to-Japanese and Japanese-to-English directions. The experiment also shows that the SSSS transfer method significantly improves structural appropriateness in the translated sentences in both translation directions, which is indicated by substantial gains over 30 points in RIBES scores.