Tools
ToolsPICKARD, Thomas (2020). Comparing word2vec and GloVe for Automatic Measurement of MWE Compositionality. In: MARKANTONATOU, Stella, MCCRAE, John, MITROVIĆ, Jelena, TIBERIUS, Carole, RAMISCH, Carlos, VAIDYA, Ashwini, OSENOVA, Petya and SAVARY, Agata, (eds.) Proceedings of the Joint Workshop on Multiword Expressions and Electronic Lexicons. Online, Association for Computational Linguistics, 95-100. [Book Section]
Documents
37452:1405404
Preview
PDF
Pickard-ComparingWord2vecAndGlove(VoR).pdf - Published Version
Available under License Creative Commons Attribution.
Pickard-ComparingWord2vecAndGlove(VoR).pdf - Published Version
Available under License Creative Commons Attribution.
Download (193kB) | Preview
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.
More Information
Statistics
Downloads
Downloads per month over past year
Metrics
Altmetric Badge
Dimensions Badge
Share
Actions (login required)
 |
View Item |