Denoising Distant Supervision for Relation Extraction via Instance-Level Adversarial Training
arXiv:1805.10959
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.
References in corpus (7)
- Explaining and Harnessing Adversarial Examples
- On the Properties of Neural Machine Translation: Encoder-Decoder Approaches
- Distributional Smoothing with Virtual Adversarial Training
- Relation Classification via Recurrent Neural Network
- End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures
- Data Noising as Smoothing in Neural Network Language Models
- Classifying Relations by Ranking with Convolutional Neural Networks
Cited by in corpus (7)
- More Data, More Relations, More Context and More Openness: A Review and Outlook for Relation Extraction
- Finding Influential Instances for Distantly Supervised Relation Extraction
- Modeling relation paths for knowledge base completion via joint adversarial training
- RH-Net: Improving Neural Relation Extraction via Reinforcement Learning and Hierarchical Relational Searching
- Manual Evaluation Matters: Reviewing Test Protocols of Distantly Supervised Relation Extraction
- SENT: Sentence-level Distant Relation Extraction via Negative Training
- Deep Ranking Based Cost-sensitive Multi-label Learning for Distant Supervision Relation Extraction