On the Correlation of Word Embedding Evaluation Metrics - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020) Year : 2020

On the Correlation of Word Embedding Evaluation Metrics

Abstract

Word embeddings intervene in a wide range of natural language processing tasks. These geometrical representations are easy to manipulate for automatic systems. Therefore, they quickly invaded all areas of language processing. While they surpass all predecessors, it is still not straightforward why and how they do so. In this article, we propose to investigate all kind of evaluation metrics on various datasets in order to discover how they correlate with each other. Those correlations lead to 1) a fast solution to select the best word embeddings among many others, 2) a new criterion that may improve the current state of static Euclidean word embeddings, and 3) a way to create a set of complementary datasets, i.e. each dataset quantifies a different aspect of word embeddings.
Fichier principal
Vignette du fichier
2020.lrec-1.589.pdf (1.25 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02919006 , version 1 (24-08-2020)

Identifiers

  • HAL Id : hal-02919006 , version 1

Cite

François Torregrossa, Vincent Claveau, Nihel Kooli, Guillaume Gravier, Robin Allesiardo. On the Correlation of Word Embedding Evaluation Metrics. LREC 2020 - 12th Conference on Language Resources and Evaluation, May 2020, Marseille, France. pp.4789 - 4797. ⟨hal-02919006⟩
129 View
155 Download

Share

Gmail Facebook X LinkedIn More