Publication at Faculty of Mathematics and Physics |
2013
Abstract
This paper presents a comparative study of 5 different types of Word Space Models (WSMs) combined with 4 different compositionality measures applied to the task of automatically determining semantic compositionality of word expressions. Many combinations of WSMs and measures have never been applied to the task before.
The study follows Biemann and Giesbrecht (2011) who attempted to find a list of expressions for which the compositionality assumption – the meaning of an expression is determined by the meaning of its constituents and their combination does not hold. Our results are very promising and can be appreciated by those interested in WSMs, compositionali