We describe a method for the fully automatic learning of hierarchical finite state translation models. The input to the method is transcribed speech utterances and their correspon...
Inflection and derivation have been the main ways of creating new words in English. With the development of science and technology, words as such appear faster than ever in scient...
In this paper we compare and contrast two approaches to Machine Translation (MT): the CMU-UKA Syntax Augmented Machine Translation system (SAMT) and UPC-TALP N-gram-based Statisti...
In kernel methods, an interesting recent development seeks to learn a good kernel from empirical data automatically. In this paper, by regarding the transductive learning of the k...
Bracketing Transduction Grammar (BTG) is a natural choice for effective integration of desired linguistic knowledge into statistical machine translation (SMT). In this paper, we p...