Denoising Distant Supervision for Relation Extraction via Instance-Level Adversarial Training
This work addresses noise issues in relation extraction for natural language processing applications, representing an incremental improvement over existing denoising methods.
The paper tackles the wrong labeling problem in neural relation extraction models that rely on distant supervision by proposing an instance-level adversarial training mechanism to denoise data, achieving significant improvements over state-of-the-art models on a large-scale benchmark dataset.
Existing neural relation extraction (NRE) models rely on distant supervision and suffer from wrong labeling problems. In this paper, we propose a novel adversarial training mechanism over instances for relation extraction to alleviate the noise issue. As compared with previous denoising methods, our proposed method can better discriminate those informative instances from noisy ones. Our method is also efficient and flexible to be applied to various NRE architectures. As shown in the experiments on a large-scale benchmark dataset in relation extraction, our denoising method can effectively filter out noisy instances and achieve significant improvements as compared with the state-of-the-art models.