Distributional composition using higher-order dependency vectors

Weeds, Julie, Weir, David and Reffin, Jeremy (2014) Distributional composition using higher-order dependency vectors. 2nd Workshop on Continuous Space Vector Models and their Composition (EACL 2014 Workshop), Gothenberg, Sweden, April 26-30, 2014. Published in: Proceedings of the 2nd Workshop on Continuous Vector Space Models and their Compositionality (CVSC). 11-20. Association for Computational Linguistics (ACL)

[img] PDF - Published Version
Download (215kB)

Abstract

This paper concerns how to apply compositional methods to vectors based on grammatical dependency relation vectors. We demonstrate the potential of a novel approach which uses higher-order grammatical dependency relations as features. We apply the approach to adjective-noun compounds with promising results in the prediction of the vectors for (held-out) observed phrases.

Item Type: Conference Proceedings
Additional Information: W14-1502
Schools and Departments: School of Engineering and Informatics > Informatics
Depositing User: Julie Weeds
Date Deposited: 05 Feb 2016 13:45
Last Modified: 24 Jan 2019 15:18
URI: http://sro.sussex.ac.uk/id/eprint/59569

View download statistics for this item

📧 Request an update