NLP systems for tasks such as question answering and information extraction typically rely on statistical parsers. But the efficacy of such parsers can be surprisingly low, partic...
Alexander Yates, Stefan Schoenmackers, Oren Etzion...
We describe the name analysis and pronunciation component in the German version of the Bell Labs multilingual text-tospeech system. We concentrate on street names because they enc...
Classification methods from statistical pattern recognition, neural nets, and machine learning were applied to four real-world data sets. Each of these data sets has been previous...
For decades, Hidden Markov Models (HMMs) have been the state-of-the-art technique for acoustic modeling despite their unrealistic independence assumptions and the very limited rep...
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...