This paper describes the Arabic broadcast transcription system fielded by IBM in the GALE Phase 3.5 machine translation evaluation. Key advances compared to our Phase 2.5 system ...
George Saon, Hagen Soltau, Upendra Chaudhari, Step...
This paper describes an animated conversational agent called Kare1 which integrates a talking head interface with a linguistically motivated human-machine dialogue system. The age...
This paper addresses the problem of extending an adaptive information filtering system to make decisions about the novelty and redundancy of relevant documents. It argues that rel...
Support vector machines (SVMs) have proven to be a powerful technique for pattern classification. SVMs map inputs into a high dimensional space and then separate classes with a hy...
William M. Campbell, Joseph P. Campbell, Douglas A...
We present a novel paradigm for statistical machine translation (SMT), based on a joint modeling of word alignment and the topical aspects underlying bilingual document-pairs, via...