Weeds, Julie, Kober, Thomas, Reffin, Jeremy and Weir, David (2017) When a red herring is not a red herring: using compositional methods to detect non-compositional phrases. Published in: Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics [Valencia, Spain, April 3-7, 2017]: Volume 2, Short Papers. 529-534. ISBN 9781945626357

PDF - Accepted Version Restricted to SRO admin only Download (196kB)

Abstract

Non-compositional phrases such as `red herring' and weakly compositional phrases such as `spelling bee' are an integral part of natural language (Sag, 2002). They are also the phrases that are difficult, or even impossible, for good compositional distributional models of semantics. Compositionality detection therefore provides a good testbed for compositional methods. We compare an integrated compositional distributional approach, using sparse high dimensional representations, with the ad-hoc compositional approach of applying simple composition operations to state-of-the-art neural embeddings.

Item Type:	Conference Proceedings
Keywords:	distributional semantics, composition, compositionality, distributed representations
Schools and Departments:	School of Engineering and Informatics > Informatics
Subjects:	Q Science > QA Mathematics > QA0075 Electronic computers. Computer science
Depositing User:	Julie Weeds
Date Deposited:	19 Apr 2017 07:23
Last Modified:	19 Apr 2017 09:33
URI:	http://srodev.sussex.ac.uk/id/eprint/66816

View download statistics for this item

📧 Request an update