Domain Collocation Identification

Warning

This publication doesn't include Faculty of Arts. It includes Faculty of Informatics. Official publication website can be found on muni.cz.
Authors

MATERNA Jiří

Year of publication 2009
Type Article in Proceedings
Conference RASLAN 2009 : Recent Advances in Slavonic Natural Language Processing
MU Faculty or unit

Faculty of Informatics

Citation
Web https://nlp.fi.muni.cz/raslan/2009/papers/3.pdf
Field Informatics
Keywords collocation; domain; information retrieval
Description In this paper we present a new method of automatic collocation identification. Collocation is an important relation between words, which is widely used, among others, in information retrieval tasks. Over the last years, many methods of automatic collocation acquisition from text corpora have been proposed. The approach described in this paper differs from the others by focusing on domain collocations. By the domain collocation we mean a collocation which is specific for a relatively small set of documents related to the same topic. The proposed method has been implemented and used in a real information retrieval system. Comparing to the common non-domain approach, the precision of the system has increased significantly.
Related projects:

You are running an old browser version. We recommend updating your browser to its latest version.