DMCA
Retrieval models for genre classification (2008)
| Venue: | Scandinavian Journal of Information Systems |
| Citations: | 2 - 1 self |
BibTeX
@ARTICLE{Stein08retrievalmodels,
author = {Benno Stein and Sven Meyer Zu Eissen},
title = {Retrieval models for genre classification},
journal = {Scandinavian Journal of Information Systems},
year = {2008}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Abstract. Genre provides a characterization of a document with respect to its form or functional trait. Genre is orthogonal to topic, rendering genre information a powerful filter technology for information seekers in digital li-braries. However, an efficient means for genre classification is an open and controversially discussed issue. This paper gives an overview and presents new results related to automatic genre classification of text documents. We present a comprehensive survey which contrasts the genre retrieval models that have been developed for Web and non-Web corpora. With the concept of genre-specific core vocabularies the paper provides an original contribu-tion related to computational aspects and classification performance of genre retrieval models: we show how such vocabularies are acquired automatical-ly and introduce new concentration measures that quantify the vocabulary distribution in a sensible way. Based on these findings we construct light-weight genre retrieval models and evaluate their discriminative power and computational efficiency. The presented concepts go beyond the existing utilization of vocabulary-centered, genre-revealing features and open new possibilities for the construction of genre classifiers that operate in real-time. Key words: genre analysis, retrieval models, analysis and evaluation.
Keyphrases
retrieval model genre classification genre retrieval model sensible way vocabulary distribution efficient mean genre analysis information seeker present new result powerful filter technology genre-specific core vocabulary key word text document comprehensive survey computational aspect new concentration measure automatic genre classification classification performance presented concept genre information open new possibility genre classifier non-web corpus functional trait light-weight genre retrieval model genre-revealing feature discussed issue original contribu-tion computational efficiency digital li-braries discriminative power
