BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:A Study on Similarity and Relatedness Using Distributional and Wor
 dNet-based Approaches - Stephen Clark (Computer Laboratory)
DTSTART:20090511T120000Z
DTEND:20090511T130000Z
UID:TALK18266@talks.cam.ac.uk
CONTACT:Diarmuid Ó Séaghdha
DESCRIPTION:At this session of the NLIP Reading Group we'll be discussing 
 the following paper:\n\nEneko Agirre\, Enrique Alfonseca\, Keith Hall\, Ja
 na Kravalova\, Marius Pasca and Aitor Soroa. 2009. "A Study on Similarity 
 and Relatedness Using Distributional and WordNet-based Approaches":http://
 alfonseca.org/pubs/2009-naacl-long.pdf. In Proceedings of NAACL-HLT 2009.\
 n\n*Abstract:*\nThis paper presents and compares WordNet-based and distrib
 utional similarity approaches. The strengths and weaknesses of each approa
 ch regarding similarity and relatedness tasks are discussed\, and a combin
 ation is presented. Each of our methods independently provide the best res
 ults in their class on the RG and WordSim353 datasets\, and a supervised c
 ombination of them yields the best published results on all datasets. Fina
 lly\, we pioneer cross-lingual similarity\, showing that our methods are e
 asily adapted for a cross-lingual task with minor losses.\n
LOCATION:GS15\, Computer Laboratory
END:VEVENT
END:VCALENDAR