Learning mechanism in machine translation system "PIVOT"

Authors:
Mitsugu Miura;Mikito Hirata;Nawi Hoshino
Affiliations:
NEC Corporation, Tokyo, Japan;NEC Corporation, Tokyo, Japan;NEC Corporation, Tokyo, Japan
Venue:
COLING '92 Proceedings of the 14th conference on Computational linguistics - Volume 2
Year:
1992

Citing 2
Cited 0

A framework of a mechanical translation between Japanese and English by analogy principle

Proc. of the international NATO symposium on Artificial and human intelligence
Toward memory-based reasoning

Communications of the ACM - Special issue on parallelism

Quantified Score

Hi-index	0.00

Visualization

Abstract

NEC's machine translation system "PIVOT" provides analysis editing functions. The user can interactively correct errors in analysis results, such as dependency and case. However, without a learning mechanism, the user must correct similar dependency errors several times. We discuss the learning mechanism to utilize dependency and case information specified by the user. We compare four types of matching methods by simulation and show non-restricted best matching is the most effective.