Use of Source-language Context in Statistical Machine Translation: Integrating Source-language Context into the State-of-the-art Statistical Machine Translation Models

The translation features typically used in state-of-the-art statistical machine translation (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 phrase-based SMT (PB-SMT) and hierarchical PB-SMT (HPB-SMT), and can positively influence the weighting and selection of target phrases, and thus improve translation quality. In this book we present novel approaches to incorporate source-language contextual modelling into the state-of-the-art SMT models in order to enhance the quality of lexical selection. We investigate the effectiveness of use of a range of contextual features, including lexical features of neighbouring words, part-of-speech tags, supertags, sentence-similarity features, dependency information, and semantic roles. We explored a series of language pairs featuring typologically different languages, and examined the scalability of our research to larger amounts of training data.