Posts by Collection

portfolio

publications

Analogies minus analogy test: measuring regularities in word embeddings

Published in CoNLL 2020 conference, 2020

Vector space models of words have long been claimed to capture linguistic regularities as simple vector translations, but problems have been raised with this claim. We decompose and empirically analyze the classic arithmetic word analogy test, to motivate two new metrics that address the issues with the standard test, and which distinguish between class-wise offset concentration (similar directions between pairs of words drawn from different broad classes, such as France-London, China-Ottawa,…) and pairing consistency (the existence of a regular transformation between correctly-matched pairs such as France:Paris::China:Beijing). We show that, while the standard analogy test is flawed, several popular word embeddings do nevertheless encode linguistic regularities.

Recommended citation: Fournier, E. (2020). Analogies minus analogy test: measuring regularities in word embeddings. In Proceedings of the 24th Conference on Computational Natural Language Learning (pp. 365–375). Association for Computational Linguistics. http://academicpages.github.io/files/analogies_minus_analogy_test.pdf

talks

teaching

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015

This is a description of a teaching experience. You can use markdown like any other post.