Improving Unsupervised Vector-Space Thematic Fit Evaluation via Role-Filler Prototype Clustering Inproceedings
Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Association for Computational Linguistics, pp. 21-31, Denver, Colorado, 2015.Most recent unsupervised methods in vector space semantics for assessing thematic fit (e.g. Erk, 2007; Baroni and Lenci, 2010; Sayeed and Demberg, 2014) create prototypical rolefillers without performing word sense disambiguation. This leads to a kind of sparsity problem: candidate role-fillers for different senses of the verb end up being measured by the same “yardstick”, the single prototypical role-filler.
In this work, we use three different feature spaces to construct robust unsupervised models of distributional semantics. We show that correlation with human judgements on thematic fit estimates can be improved consistently by clustering typical role-fillers and then calculating similarities of candidate rolefillers with these cluster centroids. The suggested methods can be used in any vector space model that constructs a prototype vector from a non-trivial set of typical vectors
@inproceedings{greenberg-sayeed-demberg:2015:NAACL-HLT,
title = {Improving Unsupervised Vector-Space Thematic Fit Evaluation via Role-Filler Prototype Clustering},
author = {Clayton Greenberg and Asad Sayeed and Vera Demberg},
url = {http://www.aclweb.org/anthology/N15-1003},
year = {2015},
date = {2015},
booktitle = {Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
pages = {21-31},
publisher = {Association for Computational Linguistics},
address = {Denver, Colorado},
abstract = {Most recent unsupervised methods in vector space semantics for assessing thematic fit (e.g. Erk, 2007; Baroni and Lenci, 2010; Sayeed and Demberg, 2014) create prototypical rolefillers without performing word sense disambiguation. This leads to a kind of sparsity problem: candidate role-fillers for different senses of the verb end up being measured by the same “yardstick”, the single prototypical role-filler.
In this work, we use three different feature spaces to construct robust unsupervised models of distributional semantics. We show that correlation with human judgements on thematic fit estimates can be improved consistently by clustering typical role-fillers and then calculating similarities of candidate rolefillers with these cluster centroids. The suggested methods can be used in any vector space model that constructs a prototype vector from a non-trivial set of typical vectors},
pubstate = {published},
type = {inproceedings}
}