Paper Info
Title
Using domain information for word sense disambiguation
Abstract
The major goal in ITC-irst's participation at Senseval-2 was to test the role of domain information in word sense disambiguation. The underlying working hypothesis is that domain labels, such as Medicine, Architecture and Sport provide a natural way to establish semantic relations among word senses, which can be profitably used during the disambiguation process. For each task in which we participated (i.e. English all words, English 'lexical sample' and Italian 'lexical sample') a different mix of knowledge based and statistical techniques were implemented.
Year
Venue
Keywords
2001
SENSEVAL@ACL
word sense disambiguation,major goal,different mix,word sense,lexical sample,statistical technique,domain information,domain label,disambiguation process,semantic relation,profitability
Field
DocType
Citations 
Architecture,SemEval,Computer science,Working hypothesis,Artificial intelligence,Natural language processing,Linguistics,Word-sense disambiguation
Conference
33
PageRank 
References 
Authors
3.23
2
4
Name
Order
Citations
PageRank
Bernardo Magnini12027226.13
Carlo Strapparava22564230.59
Giovanni Pezzulo351248.50
Alfio Gliozzo425724.97