Frustratingly Easy Meta-Embedding -- Computing Meta-Embeddings by Averaging Source Word Embeddings



Coates, Joshua and Bollegala, Danushka ORCID: 0000-0003-4476-7003
(2018) Frustratingly Easy Meta-Embedding -- Computing Meta-Embeddings by Averaging Source Word Embeddings. .

[img] Text
average-meta-embedding.pdf - Accepted Version

Download (208kB)

Abstract

Creating accurate meta-embeddings from pre-trained source embeddings has received attention lately. Methods based on global and locally-linear transformation and concatenation have shown to produce accurate meta-embeddings. 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 or Workshop 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: 07 Jun 2022 21:10
Related URLs:
URI: https://livrepository.liverpool.ac.uk/id/eprint/3018858