Empower Distantly Supervised Relation Extraction with Collaborative Adversarial Training

by   Tao Chen, et al.

With recent advances in distantly supervised (DS) relation extraction (RE), considerable attention is attracted to leverage multi-instance learning (MIL) to distill high-quality supervision from the noisy DS. Here, we go beyond label noise and identify the key bottleneck of DS-MIL to be its low data utilization: as high-quality supervision being refined by MIL, MIL abandons a large amount of training instances, which leads to a low data utilization and hinders model training from having abundant supervision. In this paper, we propose collaborative adversarial training to improve the data utilization, which coordinates virtual adversarial training (VAT) and adversarial training (AT) at different levels. Specifically, since VAT is label-free, we employ the instance-level VAT to recycle instances abandoned by MIL. Besides, we deploy AT at the bag-level to unleash the full potential of the high-quality supervision got by MIL. Our proposed method brings consistent improvements (  5 absolute AUC score) to the previous state of the art, which verifies the importance of the data utilization issue and the effectiveness of our method.


page 2

page 3

page 4

page 5

page 6

page 7

page 8

page 9


Denoising Distant Supervision for Relation Extraction via Instance-Level Adversarial Training

Existing neural relation extraction (NRE) models rely on distant supervi...

Rewarding Coreference Resolvers for Being Consistent with World Knowledge

Unresolved coreference is a bottleneck for relation extraction, and high...

Finding Influential Instances for Distantly Supervised Relation Extraction

Distant supervision has been demonstrated to be highly beneficial to enh...

Adversarial training for multi-context joint entity and relation extraction

Adversarial training (AT) is a regularization method that can be used to...

RDSGAN: Rank-based Distant Supervision Relation Extraction with Generative Adversarial Framework

Distant supervision has been widely used for relation extraction but suf...

Distantly Supervised Relation Extraction in Federated Settings

This paper investigates distantly supervised relation extraction in fede...

A Simple, Strong and Robust Baseline for Distantly Supervised Relation Extraction

Distantly supervised relation extraction (DS-RE) is generally framed as ...