English

Progressive Adversarial Learning for Bootstrapping: A Case Study on Entity Set Expansion

Computation and Language 2021-09-27 v1

Abstract

Bootstrapping has become the mainstream method for entity set expansion. Conventional bootstrapping methods mostly define the expansion boundary using seed-based distance metrics, which heavily depend on the quality of selected seeds and are hard to be adjusted due to the extremely sparse supervision. In this paper, we propose BootstrapGAN, a new learning method for bootstrapping which jointly models the bootstrapping process and the boundary learning process in a GAN framework. Specifically, the expansion boundaries of different bootstrapping iterations are learned via different discriminator networks; the bootstrapping network is the generator to generate new positive entities, and the discriminator networks identify the expansion boundaries by trying to distinguish the generated entities from known positive entities. By iteratively performing the above adversarial learning, the generator and the discriminators can reinforce each other and be progressively refined along the whole bootstrapping process. Experiments show that BootstrapGAN achieves the new state-of-the-art entity set expansion performance.

Keywords

Cite

@article{arxiv.2109.12082,
  title  = {Progressive Adversarial Learning for Bootstrapping: A Case Study on Entity Set Expansion},
  author = {Lingyong Yan and Xianpei Han and Le Sun},
  journal= {arXiv preprint arXiv:2109.12082},
  year   = {2021}
}

Comments

Accepted to the main conference of EMNLP2021

R2 v1 2026-06-24T06:18:15.888Z