SynSetExpan: An Iterative Framework for Joint Entity Set Expansion and Synonym Discovery

TL;DR

SynSetExpan introduces an iterative framework that jointly improves entity set expansion and synonym discovery by leveraging their interdependence, validated on a new large-scale dataset and benchmarks.

Contribution

The paper proposes a novel iterative framework that jointly enhances entity set expansion and synonym discovery, and introduces the first large-scale dataset for these tasks.

Findings

Effective in improving both entity set expansion and synonym discovery.

Outperforms previous methods on SE2 dataset and benchmarks.

Creates the first large-scale dataset for joint study of these tasks.

Abstract

Entity set expansion and synonym discovery are two critical NLP tasks. Previous studies accomplish them separately, without exploring their interdependencies. In this work, we hypothesize that these two tasks are tightly coupled because two synonymous entities tend to have similar likelihoods of belonging to various semantic classes. This motivates us to design SynSetExpan, a novel framework that enables two tasks to mutually enhance each other. SynSetExpan uses a synonym discovery model to include popular entities' infrequent synonyms into the set, which boosts the set expansion recall. Meanwhile, the set expansion model, being able to determine whether an entity belongs to a semantic class, can generate pseudo training data to fine-tune the synonym discovery model towards better accuracy. To facilitate the research on studying the interplays of these two tasks, we create the first large-scale Synonym-Enhanced Set Expansion (SE2) dataset via crowdsourcing. Extensive experiments on the SE2 dataset and previous benchmarks demonstrate the effectiveness of SynSetExpan for both entity set expansion and synonym discovery tasks.