Paper Info
Title
Automatic Paragraph Identification: A Study across Languages and Domains
Abstract
In this paper we investigate whether paragraphs can be identified automatically in different languages and domains. We propose a machine learning ap- proach which exploits textual and discourse cues and we assess how well humans perform on this task. Our best models achieve an accuracy that is significantly higher than the best baseline and, for most data sets, comes to within 6% of human per- formance.
Year
Venue
Keywords
2004
EMNLP
machine learning,human performance
Field
DocType
Volume
Computer science,Paragraph,Artificial intelligence,Natural language processing,Linguistics
Conference
W04-32
Citations 
PageRank 
References 
5
0.55
9
Authors
2
Name
Order
Citations
PageRank
Caroline Sporleder145331.84
Mirella Lapata25973369.52