# DSGAN: Generative Adversarial Training for Distant Supervision Relation Extraction

arXiv: https://arxiv.org/abs/1805.09929 · HTML: https://mlsanity.com/paper/1805.09929/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 May 2018.

## Built on by (most cited first, 23 of 23)

- [Large Scale Image Completion via Co-Modulated Generative Adversarial Networks](https://mlsanity.com/paper/2103.10428/) (2021)
- [Document-Level Relation Extraction with Adaptive Focal Loss and Knowledge Distillation](https://mlsanity.com/paper/2203.10900/) (2022)
- [Prototypical Representation Learning for Relation Extraction](https://mlsanity.com/paper/2103.11647/) (2021)
- [ATM: Adversarial Tuning Multi-agent System Makes a Robust Retrieval-Augmented Generator](https://mlsanity.com/paper/2405.18111/) (2024)
- [Deep Neural Approaches to Relation Triplets Extraction: A Comprehensive Survey](https://mlsanity.com/paper/2103.16929/) (2021)
- [Deep Neural Network Based Relation Extraction: An Overview](https://mlsanity.com/paper/2101.01907/) (2021)
- [Improving Distantly-Supervised Relation Extraction through BERT-based Label & Instance Embeddings](https://mlsanity.com/paper/2102.01156/) (2021)
- [Distantly-Supervised Long-Tailed Relation Extraction Using Constraint Graphs](https://mlsanity.com/paper/2105.11225/) (2021)
- [Distantly Supervised Relation Extraction with Sentence Reconstruction and Knowledge Base Priors](https://mlsanity.com/paper/2104.08225/) (2021)
- [Empower Distantly Supervised Relation Extraction with Collaborative Adversarial Training](https://mlsanity.com/paper/2106.10835/) (2021)
- [HiCLRE: A Hierarchical Contrastive Learning Framework for Distantly Supervised Relation Extraction](https://mlsanity.com/paper/2202.13352/) (2022)
- [Adaptive Prototypical Networks with Label Words and Joint Representation Learning for Few-Shot Relation Classification](https://mlsanity.com/paper/2101.03526/) (2021)
- [Uncertainty Guided Label Denoising for Document-level Distant Relation Extraction](https://mlsanity.com/paper/2305.11029/) (2023)
- [Knowing False Negatives: An Adversarial Training Method for Distantly Supervised Relation Extraction](https://mlsanity.com/paper/2109.02099/) (2021)
- [Handling Realistic Label Noise in BERT Text Classification](https://mlsanity.com/paper/2305.16337/) (2023)
- [Progressive Adversarial Learning for Bootstrapping: A Case Study on Entity Set Expansion](https://mlsanity.com/paper/2109.12082/) (2021)
- [Labeled Data Generation with Inexact Supervision](https://mlsanity.com/paper/2106.04716/) (2021)
- [Improving Distantly Supervised Relation Extraction with Self-Ensemble Noise Filtering](https://mlsanity.com/paper/2108.09689/) (2021)
- [KnowMAN: Weakly Supervised Multinomial Adversarial Networks](https://mlsanity.com/paper/2109.07994/) (2021)
- [Mention-centered Graph Neural Network for Document-level Relation Extraction](https://mlsanity.com/paper/2103.08200/) (2021)
- [Few Clean Instances Help Denoising Distant Supervision](https://mlsanity.com/paper/2209.06596/) (2022)
- [Relation Extraction Model Based on Semantic Enhancement Mechanism](https://mlsanity.com/paper/2311.02564/) (2023)
- [READ: Improving Relation Extraction from an ADversarial Perspective](https://mlsanity.com/paper/2404.02931/) (2024)

## Abstract (arXiv)

Distant supervision can effectively label data for relation extraction, but suffers from the noise labeling problem. Recent works mainly perform soft bag-level noise reduction strategies to find the relatively better samples in a sentence bag, which is suboptimal compared with making a hard decision of false positive samples in sentence level. In this paper, we introduce an adversarial learning framework, which we named DSGAN, to learn a sentence-level true-positive generator. Inspired by Generative Adversarial Networks, we regard the positive samples generated by the generator as the negative samples to train the discriminator. The optimal generator is obtained until the discrimination ability of the discriminator has the greatest decline. We adopt the generator to filter distant supervision training dataset and redistribute the false positive instances into the negative set, in which way to provide a cleaned dataset for relation classification. The experimental results show that the proposed strategy significantly improves the performance of distant supervision relation extraction comparing to state-of-the-art systems.