Automatic detection of text genre

Автоматическое определение жанра текста
Brett Kessler, Geoffrey Numberg, Hinrich Schütze
1997-01-01

computational linguisticsstructural propertiessurface cuestext classificationtext genre detection
As the text databases available to users become larger and more heterogeneous, genre becomes increasingly important for computational linguistics as a complement to topical and structural principles of classification. We propose a theory of genres as bundles of facets, which correlate with various surface cues, and argue that genre detection based on surface cues is as successful as detection based on deeper structural properties.
1
Genre facets correlate with observable surface cues, enabling automatic genre detection from textual surface features.
2
Genre is increasingly important for classifying large, heterogeneous text databases alongside topical and structural criteria.
3
The authors argue that surface-cue-based genre detection can perform as successfully as detection based on deeper structural properties.
4
The paper proposes representing text genres as bundles of facets rather than as single categorical properties.

text genre in heterogeneous text databases

automatic genre detection from surface cues compared with detection based on deeper structural properties

Publication Details
Publication Date
1997-01-01
Journal
Publisher
ISSN
Access Type
Author Information
Authors
Brett Kessler
Geoffrey Numberg
Hinrich Schütze
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat
Make a presentation
100%