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

2018/05/28 by Xu Han, Zhiyuan Liu, Han, Xu +3
Computer Science · #Adversarial Robustness in Machine Learning #Computation and Language (cs.CL) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1805.10959

openalex publication_date 2018/05/28 · openalex created_date 2018/06/01 · openalex updated_date 2026/07/28

Abstract

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.

Citations

• Relation Classification via Recurrent Neural Network
• On the Properties of Neural Machine Translation: Encoder-Decoder Approaches
• Data Noising as Smoothing in Neural Network Language Models
• Classifying Relations by Ranking with Convolutional Neural Networks

Related

• RDSGAN: Rank-based Distant Supervision Relation Extraction with Generative Adversarial Framework
• Uncover the Ground-Truth Relations in Distant Supervision: A Neural Expectation-Maximization Framework
• Improving Distantly Supervised Relation Extraction with Self-Ensemble Noise Filtering
• Denoising Relation Extraction from Document-level Distant Supervision
• Empower Distantly Supervised Relation Extraction with Collaborative Adversarial Training