Previous methods on improving translation quality by employing multiple SMT models usually carry out as a secondpass decision procedure on hypotheses from multiple systems using e...
Current SMT systems usually decode with single translation models and cannot benefit from the strengths of other models in decoding phase. We instead propose joint decoding, a met...
This paper proposes a forest-based tree sequence to string translation model for syntaxbased statistical machine translation, which automatically learns tree sequence to string tr...
Hui Zhang, Min Zhang, Haizhou Li, AiTi Aw, Chew Li...
Statistical translation models that try to capture the recursive structure of language have been widely adopted over the last few years. These models make use of varying amounts o...
In recent work, we proposed an alternative to parallel text as translation model (TM) training data: audio recordings of parallel speech (pSp), as it occurs in any communication s...
A model of co-occurrence in bitext is a boolean predicate that indicates whether a given pair of word tokens co-occur in corresponding regions of the bitext space. Co-occurrence i...
Many multilingual NLP applications need to translate words between different languages, but cannot afford the computational expense of inducing or applying a full translation mode...
In the framework of the Tc-Star project, we analyze and propose a combination of two Statistical Machine Translation systems: a phrase-based and an N-gram-based one. The exhaustiv...
We present an extension of phrase-based statistical machine translation models that enables the straight-forward integration of additional annotation at the word-level — may it ...