# Learning with Noise: Enhance Distantly Supervised Relation Extraction with Dynamic Transition Matrix

## TL;DR

This paper introduces a dynamic transition matrix approach to mitigate noise in distantly supervised relation extraction, improving model accuracy without requiring explicit noise labels.

## Contribution

It proposes a novel curriculum learning method to train a dynamic transition matrix that characterizes and reduces noise in distantly supervised data.

## Key findings

- Consistently improves relation extraction accuracy
- Outperforms state-of-the-art methods across scenarios
- Effectively models noise without explicit supervision

## Abstract

Distant supervision significantly reduces human efforts in building training data for many classification tasks. While promising, this technique often introduces noise to the generated training data, which can severely affect the model performance. In this paper, we take a deep look at the application of distant supervision in relation extraction. We show that the dynamic transition matrix can effectively characterize the noise in the training data built by distant supervision. The transition matrix can be effectively trained using a novel curriculum learning based method without any direct supervision about the noise. We thoroughly evaluate our approach under a wide range of extraction scenarios. Experimental results show that our approach consistently improves the extraction results and outperforms the state-of-the-art in various evaluation scenarios.