Year: 2007
Type: conference-paper
Abstract: This paper describes the University of North Texas SubFinder system. The system is able to provide the most likely set of substitutes for a word in a given context, by combining several techniques and knowledge sources. SubFinder has successfully participated in the best and out of ten (oot) tracks in the SemEval lexical substitution task, consistently ranking in the first or second place.
Authors: Samer Hassan, Andras Csomai, Carmen Banea, Ravi Sinha, Rada Mihalcea
Institution: University of North Texas
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
Funder: University of North Texas
OpenAlex ID: W2045274176
