K. Erk and S. Pado: Paraphrase assessment in structured vector space: Exploring parameters and datasets. Proceedings of the workshop on Geometrical Models for Natural Language Semantics. Athens, Greece. 2009.
The appropriateness of paraphrases for words depends often on context: ``grab'' can replace ``catch'' in ``catch a ball'', but not in ``catch a cold''. Structured Vector Space (SVS) is a model that computes word meaning in context in order to assess the appropriateness of such paraphrases. This paper investigates ``best-practice'' parameter settings for SVS, and it presents a method to obtain large datasets for paraphrase assessment from corpora with WSD annotation.
@InProceedings{erk08:_struc_vector_space_model_word_meanin_contex,
author = {Katrin Erk and Sebastian Pad\'o},
title = {Paraphrase assessment in structured vector space:
Exploring parameters and datasets},
booktitle = {Proceedings of the workshop on Geometrical Models
for Natural Language Semantics},
year = 2009,
address = {Athens, Greece}
}