Repository logo
 

Unsupervised Cross-Lingual Information Retrieval Using Monolingual Data Only

Accepted version
Peer-reviewed

Type

Conference Object

Change log

Authors

Litschko, Robert 
Glavas, Goran 
Ponzetto, Simone Paolo 
Vulic, Ivan 

Abstract

We propose a fully unsupervised framework for ad-hoc cross-lingual information retrieval (CLIR) which requires no bilingual data at all. The framework leverages shared cross-lingual word embedding spaces in which terms, queries, and documents can be represented, irrespective of their actual language. The shared embedding spaces are induced solely on the basis of monolingual corpora in two languages through an iterative process based on adversarial neural networks. Our experiments on the standard CLEF CLIR collections for three language pairs of varying degrees of language similarity (English-Dutch/Italian/Finnish) demonstrate the usefulness of the proposed fully unsupervised approach. Our CLIR models with unsupervised cross-lingual embeddings outperform baselines that utilize cross-lingual embeddings induced relying on word-level and document-level alignments. We then demonstrate that further improvements can be achieved by unsupervised ensemble CLIR models. We believe that the proposed framework is the first step towards development of effective CLIR models for language pairs and domains where parallel data are scarce or non-existent.

Description

Keywords

Unsupervised cross-lingual IR, cross-lingual vector spaces

Journal Title

ACM/SIGIR PROCEEDINGS 2018

Conference Name

SIGIR '18: The 41st International ACM SIGIR conference on research and development in Information Retrieval

Journal ISSN

Volume Title

Publisher

ACM
Sponsorship
European Research Council (648909)