Data from the paper: Unsupervised Cross-Lingual Information Retrieval Using Monolingual Data Only



Item Type: Dataset
Title: Data from the paper: Unsupervised Cross-Lingual Information Retrieval Using Monolingual Data Only
Date: 2 May 2018
Creator: Litschko, Robert ; Glavaš, Goran ; Ponzetto, Simone Paolo ; Vulić, Ivan
Divisions (Free): University of Mannheim, Data and Web Science Group, University of Cambridge, Language Technology Lab
DDC
Classification:		 004 Computer science, internet
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.
URL: https://madata.bib.uni-mannheim.de/273/
DOI: https://doi.org/10.7801/273
Access (Controlled): Download
External URL for Other Related Materials: https://arxiv.org/abs/1805.00879

Metadata export

FileFilename / InfosLink
[img] Archive (Embedding spaces for UnsupCLIR paper)
Filename: UnsupCLIREmbeddings.tar.gz


Download (3GB)
Date Deposited: 02 May 2018 14:50
Last Modified: 05 Mar 2024 13:12

You have found an error? Please let us know about your desired correction here: E-Mail

Actions (login required)

View Item View Item
Mannheim Research Data is powered by EPrints 3 which is developed by the School of Electronics and Computer Science at the University of Southampton. More information and software credits.