High Performance Natural Language Processing on Semantic Network Array Processor

Abstract

This paper describes a natural language processing system developed for the Semantic Network Array Processor (SNAP). The goal of our work is to develop a scalable and high-performance natural language processing system which utilizes the high degree of parallelism provided by the SNAP machine. We have implemented an experimental machine translation system as a central part of a realtime speech-to-speech dialogue translation system. It is a SNAP version of the DMDIAIOG speech-tospeech translation system. Memory-based natural language processing and syntactic constraint network model has been incorporated using parallel marker-passing which is directly supported from hardware level. Experimental results demonstrate that the parsing of a sentence is done in the order of milliseconds. 1

Cite

Text

Kitano et al. "High Performance Natural Language Processing on Semantic Network Array Processor." International Joint Conference on Artificial Intelligence, 1991.

Markdown

[Kitano et al. "High Performance Natural Language Processing on Semantic Network Array Processor." International Joint Conference on Artificial Intelligence, 1991.](https://mlanthology.org/ijcai/1991/kitano1991ijcai-high/)

BibTeX

@inproceedings{kitano1991ijcai-high,
  title     = {{High Performance Natural Language Processing on Semantic Network Array Processor}},
  author    = {Kitano, Hiroaki and Moldovan, Dan I. and Cha, Seungho},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {1991},
  pages     = {911-917},
  url       = {https://mlanthology.org/ijcai/1991/kitano1991ijcai-high/}
}