Monolingual Retrieval Experiments with a Domain-Specific Document Corpus at the Chemnitz University of Technology [chapter]

Jens Kürsten, Maximilian Eibl
2007 Lecture Notes in Computer Science  
Abstr act This article describes the first participation of the Media Informatics Section of the Chemnitz Technical University at the Cross Language Evaluation Forum. A first experimental prototype is described which implements several different methods of optimizing search results. The configuration of the prototype is tested with the GIRT corpus. The results of the DomainSpecific Monolingual German task suggest that combining the suffix stripping stemming and the decompounding approach is
more » ... useful. Also, a local document clustering approach used to improve pseudo relevance feedback seems to be quite beneficial. Nevertheless, the evaluation of the English task using the same configuration suggests that the qualities of the results are highly speech dependent.
doi:10.1007/978-3-540-74999-8_26 fatcat:ocwog2mcu5fexi6gcdxq7wqhum