The Use of NLP Techniques in CLIR [chapter]

Bärbel Ripplinger
2001 Lecture Notes in Computer Science  
The application of nlp techniques to improve the results of information retrieval is still considered as a controversial issue, whereas nlp techniques in cross-language information retrieval (clir) are already well established, at least for the translation part. In this paper, the clir component -Mpro-IR -is represented which has been developed as the core module of a multilingual information system in a legal domain. This component uses not only the lexical base form for indexing but, in
more » ... on derivational information and for German information about the decomposition of compounds. This information is provided by a sophisticated morpho-syntactic analyser (mpro) and is exploited not only for query translation but also for query expansion as well as the search and the document ranking. Mpro-IR is developed for a domain with a focus on recall. The objective of the clef evaluation was to assess this linguistic based retrieval approach in an unrestricted domain. The focus of the investigation was on how derivation and decomposition can contribute to improve the recall. Due to time restriction we could only submit one cross-language run with English as query language using the phrase search component o f Mpro-IR which is restricted to search o n l y for one translation, and where the queried terms have to occur in the same sentence. These restrictions result in a small number of retrieved documents, and thus in a low performance.
doi:10.1007/3-540-44645-1_16 fatcat:shhnddsdabaztbgflxiaaedwnu