Target phrase selection, a crucial component of the state-of-the-art phrase-based statistical machine translation (PBSMT) model, plays a key role in generating accurate translation...
Rejwanul Haque, Sudip Kumar Naskar, Andy Way, Mart...
In this paper, we present a novel approach to enhance hierarchical phrase-based machine translation systems with linguistically motivated syntactic features. Rather than directly ...
Word and n-gram posterior probabilities estimated on N-best hypotheses have been used to improve the performance of statistical machine translation (SMT) in a rescoring framework....
Abstract One of the main hurdles to improved CLIR effectiveness is resolving ambiguity associated with translation. Availability of resources is also a problem. First we present a ...
We present two methods for estimating replacement probabilities without using parallel corpora. The first method proposed exploits the possible translation probabilities latent in ...