Current statistical machine translation (SMT) systems are trained on sentencealigned and word-aligned parallel text collected from various sources. Translation model parameters ar...
Spyros Matsoukas, Antti-Veikko I. Rosti, Bing Zhan...
Though most translation systems have some mechanism for translating certain types of divergent predicate-argument structures, they do not provide a genera] procedure that takes ad...
This paper presents a partial matching strategy for phrase-based statistical machine translation (PBSMT). Source phrases which do not appear in the training corpus can be translat...
In this paper we present an application of explanation-based learning (EBL) in the parsing module of a real-time English-Spanish machine translation system designed to translate c...
Janine Toole, Fred Popowich, Devlan Nicholson, Dav...
In current phrase-based Statistical Machine Translation systems, more training data is generally better than less. However, a larger data set eventually introduces a larger model ...