First International Conference on Spoken Language Processing (ICSLP 90)

Kobe, Japan
November 18-22, 1990

Massively Parallel Spoken Language Processing using a Parallel Associative Processor IXM2

Hiroaki Kitano (1,2), Tetsuya Higuchi (1,3), Masaru Tomita (1)

(1) Center for Machine Translation, Carnegie Mellon University, Pittsburgh, PA, USA
(2) NEC Corporation, Tokyo, Japan
(3) Electrotechnical Laboratory, Ibaraki, Japan

This paper reports experimental results of a natural language processing scheme for spoken inputs implemented on a massively parallel machine IXM2. We have carried out performance tests on language models on IXM2 including a word-pair grammar and a memory-based parsing. Experimental results demonstrate that use of IXM2 as a language processing engine for certain language models is a promising approach in attaining a real-time response. Syntactic recognition completes in a few milli-seconds. Plus, response time grows only linearly to the length of the input sentences, attaining approximately of order o(ri).

Full Paper

Bibliographic reference.  Kitano, Hiroaki / Higuchi, Tetsuya / Tomita, Masaru (1990): "Massively parallel spoken language processing using a parallel associative processor IXM2", In ICSLP-1990, 917-920.