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

Lingyong Yan, Xianpei Han, Le Sun


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.
Anthology ID:
2021.emnlp-main.762
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9673–9682
Language:
URL:
https://aclanthology.org/2021.emnlp-main.762
DOI:
10.18653/v1/2021.emnlp-main.762
Bibkey:
Cite (ACL):
Lingyong Yan, Xianpei Han, and Le Sun. 2021. Progressive Adversarial Learning for Bootstrapping: A Case Study on Entity Set Expansion. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 9673–9682, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Progressive Adversarial Learning for Bootstrapping: A Case Study on Entity Set Expansion (Yan et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.762.pdf
Code
 lingyongyan/bootstrapgan