Take and Took, Gaggle and Goose, Book and Read: Evaluating the Utility of Vector Differences for Lexical Relation Learning

TL;DR

This paper evaluates how effectively vector differences in word embeddings capture various lexical relations across different learning methods, demonstrating broad applicability and generalization to unseen words.

Contribution

It systematically assesses the utility of vector subtraction for lexical relation learning across multiple settings, expanding understanding beyond analogy tasks.

Findings

Vector differences encode diverse lexical relations.

Supervised training improves relation classification accuracy.

Method generalizes well to unseen lexical items.

Abstract

Recent work on word embeddings has shown that simple vector subtraction over pre-trained embeddings is surprisingly effective at capturing different lexical relations, despite lacking explicit supervision. Prior work has evaluated this intriguing result using a word analogy prediction formulation and hand-selected relations, but the generality of the finding over a broader range of lexical relation types and different learning settings has not been evaluated. In this paper, we carry out such an evaluation in two learning settings: (1) spectral clustering to induce word relations, and (2) supervised learning to classify vector differences into relation types. We find that word embeddings capture a surprising amount of information, and that, under suitable supervised training, vector subtraction generalises well to a broad range of relations, including over unseen lexical items.