Translation techniques in cross-language information retrieval
By Dong Zhou, Mark Truran, T. Brailsford, Vincent P. Wade, Helen Ashman. CSUR, 2012
615 citations recorded by the source corpus.
Cross-language information retrieval (CLIR) is an active sub-domain of information retrieval (IR). Like IR, CLIR is centered on the search for documents and for information contained within those documents. Unlike IR, CLIR must reconcile queries and documents that are written in different languages. The usual solution to this mismatch involves translating the query and/or the documents before performing the search. Translation is therefore a pivotal activity for CLIR engines. Over the last 15 years, the CLIR community has developed a wide range of techniques and models supporting free text translation. This article presents an overview of those techniques, with a special emphasis on recent developments.
Subfields: Artificial Intelligence
View Paper: https://www.semanticscholar.org/paper/4fbe1e8f65f4c71565e8e6eb47c0c3a78a182bf3
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Ondrej Dusek
- Ales Tamchyna
- Martin Popel
- Rudolf Rosa
- David Marecek
- Michal Novák
- Gareth J. F. Jones
- Jan Hajic
Citations in the corpus
- Adaptation of machine translation for multilingual information retrieval in the medical domain (2014, background): “The major issues one has to face in query translation are ambiguity and low coverage [108].”
- What Drives Cross-lingual Ranking? Retrieval Approaches with Multilingual Language Models (2025, unknown): “In addition, the translation step introduces latency and inconsistency in large-scale systems [11, 25], making explicit query translation less feasible in operational settings.”