Integrating source-language context into phrase-based statistical machine translation

Abstract

The translation features typically used in Phrase-Based Statistical Machine Translation (PB-SMT) model dependencies between the source and target phrases, but not among the phrases in the source language themselves. A swathe of research has demonstrated that integrating source context modelling directly into log-linear PB-SMT can positively influence the weighting and selection of target phrases, and thus improve translation quality. In this contribution we present a revised, extended account of our previous work on using a range of contextual features, including lexical features of neighbouring words, supertags, and dependency information. We add a number of novel aspects, including the use of semantic roles as new contextual features in PB-SMT, adding new language pairs, and examining the scalability of our research to larger amounts of training data. While our results are mixed across feature selections, classifier hyperparameters, language pairs, and learning curves, we observe that including contextual features of the source sentence in general produces improvements. The most significant improvements involve the integration of long-distance contextual features, such as dependency relations in combination with part-of-speech tags in Dutch-to-English subtitle translation, the combination of dependency parse and semantic role information in English-to-Dutch parliamentary debate translation, or supertag features in English-to-Chinese translation.