SynSetExpan: An Iterative Framework for Joint Entity Set Expansion and Synonym Discovery
This work addresses the interdependencies between entity set expansion and synonym discovery for NLP researchers, offering a novel joint approach that is incremental over prior separate methods.
The paper tackles the problem of entity set expansion and synonym discovery in NLP by proposing SynSetExpan, a framework that jointly performs these tasks to enhance each other, resulting in improved recall and accuracy as demonstrated on a new dataset and benchmarks.
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.