Given multiple translations of the same source sentence, how to combine them to produce a translation that is better than any single system output? We propose a hierarchical syste...
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...
Collocation translation is important for machine translation and many other NLP tasks. Unlike previous methods using bilingual parallel corpora, this paper presents a new method f...
In this paper, we describe a search procedure for statistical machine translation (MT) based on dynmnic programming (DP). Starting from a DP-based solution to the traveling salesm...
Our goal is to explore methods for combining structured but incomplete information from dictionaries with the unstructured but more complete information available in corpora for t...