Beyond Ranked Lists: The SARAL Framework for Cross-Lingual Document Set Retrieval

TL;DR

The SARAL framework enhances cross-lingual information retrieval by retrieving relevant document sets across languages, outperforming other methods in multilingual evaluations.

Contribution

This work introduces a novel approach for cross-lingual IR that focuses on retrieving relevant document sets rather than just ranked lists, advancing the state of CLIR.

Findings

SARAL outperformed other teams in 5 of 6 evaluation conditions

Effective retrieval of query-relevant document sets across multiple languages

Demonstrated robustness in Farsi, Kazakh, and Georgian evaluations

Abstract

Machine Translation for English Retrieval of Information in Any Language (MATERIAL) is an IARPA initiative targeted to advance the state of cross-lingual information retrieval (CLIR). This report provides a detailed description of Information Sciences Institute's (ISI's) Summarization and domain-Adaptive Retrieval Across Language's (SARAL's) effort for MATERIAL. Specifically, we outline our team's novel approach to handle CLIR with emphasis in developing an approach amenable to retrieve a query-relevant document \textit{set}, and not just a ranked document-list. In MATERIAL's Phase-3 evaluations, SARAL exceeded the performance of other teams in five out of six evaluation conditions spanning three different languages (Farsi, Kazakh, and Georgian).