Unsupervised Cross-Lingual Information Retrieval Using Monolingual Data Only
| Autor: | Ivan Vulić, Robert Litschko, Simone Paolo Ponzetto, Goran Glavaš |
|---|---|
| Jazyk: | angličtina |
| Předmět: |
FOS: Computer and information sciences
Cross lingual Computer Science - Computation and Language Word embedding Information retrieval Similarity (geometry) Basis (linear algebra) Artificial neural network Computer science InformationSystems_INFORMATIONSTORAGEANDRETRIEVAL 02 engineering and technology cross-lingual vector spaces 020204 information systems 0202 electrical engineering electronic engineering information engineering ComputingMethodologies_DOCUMENTANDTEXTPROCESSING Embedding 020201 artificial intelligence & image processing Computation and Language (cs.CL) Unsupervised cross-lingual IR |
| Zdroj: | The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval SIGIR The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval-SIGIR 18 The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval -SIGIR '18 |
| DOI: | 10.1145/3209978.3210157 |
| Popis: | 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. Comment: accepted at SIGIR'18 (preprint) |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|