RDSGAN: Rank-based Distant Supervision Relation Extraction with Generative Adversarial Framework
This work addresses false positives in relation extraction for NLP applications, representing an incremental improvement over existing denoising methods.
The paper tackles the noise labeling problem in distant supervision relation extraction by proposing RDSGAN, a generative adversarial framework that combines soft attention and hard decision to generate valid instances, achieving superior performance over strong baselines.
Distant supervision has been widely used for relation extraction but suffers from noise labeling problem. Neural network models are proposed to denoise with attention mechanism but cannot eliminate noisy data due to its non-zero weights. Hard decision is proposed to remove wrongly-labeled instances from the positive set though causes loss of useful information contained in removed instances. In this paper, we propose a novel generative neural framework named RDSGAN (Rank-based Distant Supervision GAN) which automatically generates valid instances for distant supervision relation extraction. Our framework combines soft attention and hard decision to learn the distribution of true positive instances via adversarial training and selects valid instances conforming to the distribution via rank-based distant supervision, which addresses the false positive problem. Experimental results show the superiority of our framework over strong baselines.