Frustratingly easy meta-embedding-computing meta-embeddings by averaging source word embeddings

Coates, JN and Bollegala, D ORCID: 0000-0003-4476-7003 (2018) Frustratingly easy meta-embedding-computing meta-embeddings by averaging source word embeddings In: NAACL-HLT, 2018-6-1 - 2018-6-6, New Orleans, USA.

Text average-meta-embedding.pdf - Author Accepted Manuscript Download (208kB)

Abstract

Creating accurate meta-embeddings from pretrained source embeddings has received attention lately. Methods based on global and locally-linear transformation and concatenation have shown to produce accurate metaembeddings. In this paper, we show that the arithmetic mean of two distinct word embedding sets yields a performant meta-embedding that is comparable or better than more complex meta-embedding learning methods. The result seems counter-intuitive given that vector spaces in different source embeddings are not comparable and cannot be simply averaged. We give insight into why averaging can still produce accurate meta-embedding despite the incomparability of the source vector spaces.

Item Type:	Conference Item (Unspecified)
Additional Information:	Accepted to NAACL-HLT 2018
Uncontrolled Keywords:	cs.CL, cs.CL
Depositing User:	Symplectic Admin
Date Deposited:	12 Mar 2018 09:17
Last Modified:	22 Apr 2026 04:56
Related Websites:	Author
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3018858
Disclaimer:	The University of Liverpool is not responsible for content contained on other websites from links within repository metadata. Please contact us if you notice anything that appears incorrect or inappropriate.