Weeds, Julie, Weir, David and Keller, Bill (2005) The Distributional Similarity of Sub-Parses. In: Proceedings of the ACL Workshop on Empirical Modeling of Semantic Equivalence and Entailment. Proceedings of the Conference. . Association for Computational Linguistics, Menlo Park, CA. USA, pp. 7-12. ISBN 0736-587X
![]() |
PDF
Restricted to SRO admin only Download (134kB) |
Abstract
This work explores computing distributional similarity between sub-parses, i.e., fragments of a parse tree, as an extension to general lexical distributional similarity techniques. In the same way that lexical distributional similarity is used to estimate lexical semantic similarity, we propose using distributional similarity between subparses to estimate the semantic similarity of phrases. Such a technique will allow us to identify paraphrases where the component words are not semantically similar. We demonstrate the potential of the method by applying it to a small number of examples and showing that the paraphrases are more similar than the non-paraphrases.
Item Type: | Book Section |
---|---|
Schools and Departments: | School of Engineering and Informatics > Informatics |
Subjects: | Q Science > QA Mathematics > QA0075 Electronic computers. Computer science |
Depositing User: | Chris Keene |
Date Deposited: | 27 Feb 2008 |
Last Modified: | 30 Nov 2012 16:51 |
URI: | http://srodev.sussex.ac.uk/id/eprint/1392 |
Google Scholar: | 14 Citations |
View download statistics for this item
📧 Request an update