Uncover the Ground-Truth Relations in Distant Supervision: A Neural Expectation-Maximization Framework

09/12/2019
by   Junfan Chen, et al.
0

Distant supervision for relation extraction enables one to effectively acquire structured relations out of very large text corpora with less human efforts. Nevertheless, most of the prior-art models for such tasks assume that the given text can be noisy, but their corresponding labels are clean. Such unrealistic assumption is contradictory with the fact that the given labels are often noisy as well, thus leading to significant performance degradation of those models on real-world data. To cope with this challenge, we propose a novel label-denoising framework that combines neural network with probabilistic modelling, which naturally takes into account the noisy labels during learning. We empirically demonstrate that our approach significantly improves the current art in uncovering the ground-truth relation labels.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/25/2022

Fine-grained Contrastive Learning for Relation Extraction

Recent relation extraction (RE) works have shown encouraging improvement...
research
07/12/2018

Making Efficient Use of a Domain Expert's Time in Relation Extraction

Scarcity of labeled data is one of the most frequent problems faced in m...
research
09/03/2018

Crowdsourcing Semantic Label Propagation in Relation Classification

Distant supervision is a popular method for performing relation extracti...
research
11/24/2020

Dual Supervision Framework for Relation Extraction with Distant Supervision and Human Annotation

Relation extraction (RE) has been extensively studied due to its importa...
research
05/11/2017

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

Distant supervision significantly reduces human efforts in building trai...
research
11/06/2018

DIAG-NRE: A Deep Pattern Diagnosis Framework for Distant Supervision Neural Relation Extraction

Modern neural network models have achieved the state-of-the-art performa...
research
01/12/2021

Joint Demosaicking and Denoising in the Wild: The Case of Training Under Ground Truth Uncertainty

Image demosaicking and denoising are the two key fundamental steps in di...

Please sign up or login with your details

Forgot password? Click here to reset