Text-Mining Research Group

Determining Compositionality of Word Expressions Using Various Word Space Models and Measures

This paper presents a comparative studyof 5 different types of Word Space Models(WSMs) combined with 4 differentcompositionality measures applied to thetask of automatically determining semanticcompositionality of word expressions.Many combinations of WSMs and measureshave never been applied to the taskbefore.The study follows Biemann and Giesbrecht(2011) who attempted to find a listof expressions for which the compositionalityassumption – the meaning of an expressionis determined by the meaning ofits constituents and their combination –does not hold. Our results are very promisingand can be appreciated by those interestedin WSMs, compositionality, and/orrelevant evaluation methods.

Keywords: compositionality, word expression, multiword expression, idiom, MWE, Word Space Model, WSM, measure

Year: 2013

Download:  Full text 

Lubomír Krčmář

E-mail: lkrcmar@kiv.zcu.cz

Luboš graduated from the University of West Bohemia in 2009. He is a PhD student now. His research is focused on natural language processing, information retrieval, and semantic similarity of texts of varying length. Especially, he is interested in automatic extraction of collocations and idiomatic expression from large corpora.

Karel Ježek

Phone:  +420 377632475
E-mail: jezek_ka@kiv.zcu.cz
WWW: https://cs.wikipedia.org/wiki/Karel_Je%C5%BEek_(informatik)

Karel is the former group coordinator and a supervisor of PhD students working at research projects of this Group.

Pavel Pecina

E-mail: pecina@ufal.mff.cuni.cz
WWW: http://ufal.mff.cuni.cz/~pecina/

Exploration of Semantic Spaces
Authors:	Karel Ježek, Lubomír Krčmář, Miloslav Konopík
Desc.:	This work is focused on semantic relations between words and application of these relations in research fields such as information retrieval, machine translation or document clustering.