Most statistical machine translation systems employ a word-based alignment model. In this paper we demonstrate that word-based alignment is a major cause of translation errors. We...
The University of Maryland participated in the English and Czech tasks. For English, one monolingual run using only fields based on fully automatic transcription (the required con...
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...
We present new direct data analysis showing that dynamically-built context-dependent phrasal translation lexicons are more useful resources for phrase-based statistical machine tr...
The paper introduces a query translation model that re ects the structure of the cross-language information retrieval task. The model is based on a structured bilingual dictionary...