Cross-Language Information Retrieval (CLIR) systems extend classical information retrieval mechanisms to allow users to query across languages, i.e., to retrieve documents written in languages different from the language used for query formulation. Chapter 3 discusses a range of options to implement CLIR: systems can be distinguished both by what they translate (the queries, the documents or a combination of both), and how they translate (by using machine-readable dictionaries, applying statistical approaches, or incorporating machine translation systems). Providing systems for CLIR remains difficult, with translation ambiguity and insufficient lexical coverage being among the most prominent problems. The quality of available resources for different languages also varies greatly. Combination approaches may help by leveraging multiple types of translation resources. Finally, the chapter covers the issues encountered when extending a CLIR system to handle many languages.
CITATION STYLE
Peters, C., Braschler, M., & Clough, P. (2012). Cross-Language Information Retrieval\rMultilingual Information Retrieval (pp. 57–84). Springer Berlin Heidelberg. Retrieved from http://dx.doi.org/10.1007/978-3-642-23008-0_3
Mendeley helps you to discover research relevant for your work.