---
title: "Example-Based Machine Translation on Massively Parallel Processors"
authors:
  - "Eiichiro Sumita"
  - "Kozo Oi"
  - "Osamu Furuse"
  - "Hitoshi Iida"
  - "Tetsuya Higuchi"
  - "Naoto Takahashi"
  - "Hiroaki Kitano"
doi: ""
url: "https://ijcai.org/proceedings/1993/177"
pdf: "https://ijcai.org/proceedings/1993/0177.pdf"
venue: "Proceedings of the Thirteenth International Joint Conference on Artificial Intelligence"
year: 1993
pages: "1283-1288"
track: "Natural Language"
keywords:
---

# Example-Based Machine Translation on Massively Parallel Processors

Eiichiro Sumita, Kozo Oi, Osamu Furuse, Hitoshi Iida, Tetsuya Higuchi, Naoto Takahashi, Hiroaki Kitano

*Proceedings of the Thirteenth International Joint Conference on Artificial Intelligence*, pages 1283-1288.

## Abstract

This paper describes an Example-Based Machine Translation (EBMT) system implemented on massively parallel computers. EBMT is a novel approach to machine translation that directly uses translation examples to carry out translation tasks . The authors have shown that EBMT attains substantially higher accuracy than traditional machine translation systems. However , EBMT is so computationally demanding that the system would run very slowly on sequential machines and even on a loosely-coupled multi-processor iPSC/2 . We have implemented EBMT on an IXM2 massively parallel associative memory processor and a CM-2 connection machine . Experimental results demonstrate that EBMT on the IXM2 exhibits the best performance and attains aresponse speed that will suffice for real-time tasks such as interpreting telephony.