Abstract We have introduced and are developing the notion of bilingual language modeling, an approach that shows promise for a number of aspects of statistical machine translation. A bilingual language model simultaneously generates matched strings[…]
Abstract While natural language is usually analyzed from left to right, bi-directional parsing is very attractive for both theoretical and practical reasons. In fact bi-directional parsing can exploit head information as early as possible, thus[…]
Abstract We describe a system designed for use by professional translators that enables them to dictate their translation. Because the speech recognizer has access to the source text as well as the spoken translation, a[…]
Abstract So far, speech recognition language models were constructed to minimize the per-word entropy H(W), or, what is practically the same, to maximize the probability of the training text. However, it follows directly from Information[…]
Research Groups tFast Sparse Data Training/Portability Group tLanguage Modeling for Conversational Speech Recognition tLanguage Modeling Issues for Spanish Language Large Vocabulary Continuous Speech Recognition tPhrase Structure Language Models
