Geometric Probing of Word Vectors

2021

Closed access Metadata (CSL-JSON)
DOI 10.14428/esann/2021.es2021-105
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

This paper studies the informativeness of linguistic properties such as part-of-speech and named entities encoded in word representations.First, we find directions that correspond to these properties using the method of Elazar et al. (2020).Then such directions are compared with the principal vectors obtained from application of PCA to word embeddings.As a result, we find that the part-of-speech information is more important for word embeddings than the named entity property.