Applying Machine Translation to Two-Stage Cross-Language Information Retrieval

TL;DR

This paper introduces a two-stage cross-language information retrieval method that reduces translation costs by translating only top-ranked documents after initial query translation, demonstrated with Japanese-English data.

Contribution

The paper proposes a novel two-stage CLIR approach that minimizes translation efforts by translating only a subset of documents, improving efficiency over traditional methods.

Findings

Effective retrieval with reduced translation costs

Improved accuracy by re-ranking translated documents

Demonstrated success with Japanese-English datasets

Abstract

Cross-language information retrieval (CLIR), where queries and documents are in different languages, needs a translation of queries and/or documents, so as to standardize both of them into a common representation. For this purpose, the use of machine translation is an effective approach. However, computational cost is prohibitive in translating large-scale document collections. To resolve this problem, we propose a two-stage CLIR method. First, we translate a given query into the document language, and retrieve a limited number of foreign documents. Second, we machine translate only those documents into the user language, and re-rank them based on the translation result. We also show the effectiveness of our method by way of experiments using Japanese queries and English technical documents.