A comparison of query translation methods for English-Japanese cross-language information retrieval (poster abstract)

1 August 1999

conference paper
Published by Association for Computing Machinery (ACM)

p. 269-270
https://doi.org/10.1145/312624.312690

Abstract

In this paper we report results of an investigation into EnglishJapanese Cross-Language Information Retrieval (CLIR) comparing a number of query translation methods. Results from experiments using the standard BMIR-J2 Japanese collection suggest that full machine translation (MT) can outperform popular dictionary-based query translation methods and further that in this context MT is largely robust to queries with little linguistic structure.

Keywords

MACHINE TRANSLATION

This publication has 4 references indexed in Scilit:

Lessons from BMIR-J2
Published by Association for Computing Machinery (ACM) ,1998
Experiments in Japanese text retrieval and routing using the NEAT system
Published by Association for Computing Machinery (ACM) ,1998
Resolving ambiguity for cross-language retrieval
Published by Association for Computing Machinery (ACM) ,1998
Querying across languages
Published by Association for Computing Machinery (ACM) ,1996