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...
Minimum-error-rate training (MERT) is a bottleneck for current development in statistical machine translation because it is limited in the number of weights it can reliably optimi...
Our principle objective was to reduce the error rate of speech recognition systems used by professional translators. Our work concentrated on Spanish-to-English translation. In a ...
Entities -- people, organizations, locations and the like -- have long been a central focus of natural language processing technology development, since entities convey essential ...