Improving the Precision of a Text Retrieval System with Compound Analysis (0)
| Venue: | Proceedings of the 7th Computational Linguistics in the Netherlands Meeting (CLIN |
| Citations: | 8 - 0 self |
BibTeX
@INPROCEEDINGS{Pohlmann_improvingthe,
author = {Renée Pohlmann and Wessel Kraaij},
title = {Improving the Precision of a Text Retrieval System with Compound Analysis},
booktitle = {Proceedings of the 7th Computational Linguistics in the Netherlands Meeting (CLIN},
year = {},
pages = {115--129}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
In this paper we describe research on compound analysis in the UPLIFT information retrieval project. Results of earlier experiments indicated that splitting up compounds in the query and forming new compounds by combining query terms improves recall while precision does not deteriorate. We investigated whether adding syntactic constraints to the compound splitting and formation processes would improve our initial results. We compared different strategies for compound formation and we also investigated the effect of adding compound constituents as separate index terms. The results of our experiments show that using information about head-modifier relationships to create complex index terms can improve both recall and precision significantly but only if all constituents are also added separately. We found that using both noun-adjective and noun-noun head-modifier pairs produced the best results. 1 Introduction The work described in this paper is part of the UPLIFT project 1 . UPLIFT i...
