Comparing word2vec and GloVe for Automatic Measurement of MWE Compositionality
Pickard, T
(2020)
Comparing word2vec and GloVe for Automatic Measurement of MWE Compositionality.
In:
Proceedings of the Joint Workshop on Multiword Expressions and Electronic Lexicons.
COLING 2020, The 28th International Conference on Computational Linguistics, 08-13 Dec 2020, Online.
Abstract
This paper explores the use of word2vec and GloVe embeddings for unsupervised measurement of the semantic compositionality of MWE candidates. Through comparison with several human-annotated reference sets, we find word2vec to be substantively superior to GloVe for this task. We also find Simple English Wikipedia to be a poor-quality resource for compositionality assessment, but demonstrate that a sample of 10% of sentences in the English Wikipedia can provide a conveniently tractable corpus with only moderate reduction in the quality of outputs.
Metadata
Item Type:
Proceedings Paper
Authors/Creators:
Pickard, T
Copyright, Publisher and Additional Information:
This item is protected by copyright. This work is licensed under a Creative Commons Attribution 4.0 International Licence. Licence details: http://creativecommons.org/licenses/by/4.0/.
CORE (COnnecting REpositories)
CORE (COnnecting REpositories)