Publication View

2002. Unsupervised italian word sense disambiguation using wordnets and unlabeled corpora (2002)

Abstract
This paper presents a novel method for unsupervised word sense disambiguation, which combines multiple information sources, including semantic relations, large unlabeled corpora, and cross-lingual distributional statistics. This method extends and builds on the JHU system that participated in the senseval2 exercise. Experiments performed on the senseval2 Italian lexical-sample data show signicant improvements over previously published results on this data set. 1

Publication details
Download http://citeseerx.ist.psu.edu/viewdoc/summary?doi=?doi=10.1.1.18.8258
Source http://nlp.cs.jhu.edu/~rflorian/papers/florian-wicentowski02.ps.gz
Contributors CiteSeerX
Repository CiteSeerX - Scientific Literature Digital Library and Search Engine (United States)
Type text
Language English
Relation 10.1.1.47.5135, 10.1.1.101.7518, 10.1.1.83.7385, 10.1.1.31.2473, 10.1.1.14.9320, 10.1.1.126.7186, 10.1.1.21.7749, 10.1.1.18.5155, 10.1.1.112.5267, 10.1.1.129.4273, 10.1.1.130.9518