Third International Conference on Spoken Language Processing (ICSLP 94)

Yokohama, Japan
September 18-22, 1994

Probabilistic Constraint for Integrated Speech and Language Processing

Katashi Nagao (1), Koiti Hasida (2), Takashi Miyata (3)

(1) Sony Computer Science Lab. Inc., Tokyo, Japan
(2) Electrotechnical Laboratory, Tsukuba, Japan
(3) University of Tokyo, Tokyo, Japan

A totally constraint-based computational architecture is applied to integration of speech and natural language processing. A major research issue in designing information processing systems based on constraint (level of description abstracting away from information flow) is how to guarantee global adequacy of computation. A probabilistic semantics of Horn clause programs is introduced, which is a generalization of hidden Markov models, stochastic context-free grammars, etc., and a computational method for maximum likelihood estimation is proposed. This computation deals efficiently with probabilistically dependent events, and is regarded as a sort of A* search in a general sense. Furthermore, this computational architecture supports omnidirectional information flow among heterogeneous knowledge sources, from acoustics to pragmatics, and naturally resolves problems in spoken language understanding with-out any domain/task dependent prescription of information flow.

Full Paper

Bibliographic reference.  Nagao, Katashi / Hasida, Koiti / Miyata, Takashi (1994): "Probabilistic constraint for integrated speech and language processing", In ICSLP-1994, 25-28.