We present a hierarchical phrase-based statistical machine translation in which a target sentence is efficiently generated in left-to-right order. The model is a class of synchron...
In hierarchical phrase-based SMT systems, statistical models are integrated to guide the hierarchical rule selection for better translation performance. Previous work mainly focus...
Lei Cui, Dongdong Zhang, Mu Li, Ming Zhou, Tiejun ...
A principal weakness of conventional (i.e., non-hierarchical) phrase-based statistical machine translation is that it can only exploit continuous phrases. In this paper, we extend...
Abstract. We present a systematic comparison of preprocessing techniques for two language pairs: English-Czech and English-Hindi. The two target languages, although both belonging ...
Abstract--Until quite recently, extending Phrase-based Statistical Machine Translation (PBSMT) with syntactic knowledge caused system performance to deteriorate. The most recent su...