University of Cambridge > Talks.cam > NLIP Seminar Series > Spicy adjectives and nominal donkeys: Capturing semantic deviance using compositionality in distributional spaces

Spicy adjectives and nominal donkeys: Capturing semantic deviance using compositionality in distributional spaces

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Tamara Polajnar.

Sophisticated senator and legislative onion. Whether or not you have ever heard of these things, we all have some intuition that one of them makes much less sense than the other. In this talk, I propose an approach to characterize semantic deviance of composite expressions using distributional semantic methods, that is, methods to represent word and phrase meaning based on the sets of contexts in which they occur in corpora. I present a set of simple measures extracted from distributional representations of words and phrases, and show that they are more significant in determining the acceptability of novel adjective-noun (AN) phrases than measures classically employed in studies of compound processing. Our results show that the degree of modification an adjective has on the distributional representation of a noun is the most telling factor in modelling the distinction between acceptable and deviant phrases. Thus, composition functions that are able to best estimate the degree of modification to the noun model human intuition of semantic acceptability with the best performance.

This talk is part of the NLIP Seminar Series series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2024 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity