GausSetExpander: A Simple Approach for Entity Set Expansion

TL;DR

GausSetExpander introduces an unsupervised, optimal transport-based method for entity set expansion, modeling sets as elliptical distributions and selecting entities that minimally increase set spread.

Contribution

It presents a novel, distribution-based approach to entity set expansion using optimal transport, which is unsupervised and interprets sets as elliptical distributions.

Findings

Outperforms state-of-the-art methods in experiments

Effectively models entity sets as elliptical distributions

Unsupervised approach with competitive accuracy

Abstract

Entity Set Expansion is an important NLP task that aims at expanding a small set of entities into a larger one with items from a large pool of candidates. In this paper, we propose GausSetExpander, an unsupervised approach based on optimal transport techniques. We propose to re-frame the problem as choosing the entity that best completes the seed set. For this, we interpret a set as an elliptical distribution with a centroid which represents the mean and a spread that is represented by the scale parameter. The best entity is the one that increases the spread of the set the least. We demonstrate the validity of our approach by comparing to state-of-the art approaches.