Weeds, Julie, Clarke, Daoud, Reffin, Jeremy, Weir, David and Keller, Bill (2014) Learning to distinguish hypernyms and co-hyponyms. COLING 2014, the 25th International Conference on Computational Linguistics, Dublin, Ireland, August 23-29 2014. Published in: Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers. 0 2249-2259. Dublin City University and Association for Computational Linguistics, Dublin, Ireland.

Preview

PDF - Published Version Available under License Creative Commons Attribution No Derivatives. Download (215kB) | Preview

Abstract

This work is concerned with distinguishing different semantic relations which exist between distributionally similar words. We compare a novel approach based on training a linear Support Vector Machine on pairs of feature vectors with state-of-the-art methods based on distributional similarity. We show that the new supervised approach does better even when there is minimal information about the target words in the training data, giving a 15% reduction in error rate over unsupervised approaches.

Item Type:	Conference Proceedings
Schools and Departments:	School of Engineering and Informatics > Informatics
Subjects:	P Language and Literature > P Philology. Linguistics > P0098 Computational linguistics. Natural language processing
Related URLs:	Publisher
Depositing User:	Bill Keller
Date Deposited:	27 Feb 2015 09:05
Last Modified:	20 Jan 2021 15:31
URI:	http://sro.sussex.ac.uk/id/eprint/53103

View download statistics for this item

📧 Request an update