Published on Sun Sep 05 2021

Knowing False Negatives: An Adversarial Training Method for Distantly Supervised Relation Extraction

Kailong Hao, Botao Yu, Wei Hu

Distantly supervised relation extraction (RE) automatically aligns unstructured text with relation instances in a knowledge base (KB) Due to thecompleteness of current KBs, sentences implying certain relations may be mistakenly labeled as N/A instances.

0
0
0
Abstract

Distantly supervised relation extraction (RE) automatically aligns unstructured text with relation instances in a knowledge base (KB). Due to the incompleteness of current KBs, sentences implying certain relations may be annotated as N/A instances, which causes the so-called false negative (FN) problem. Current RE methods usually overlook this problem, inducing improper biases in both training and testing procedures. To address this issue, we propose a two-stage approach. First, it finds out possible FN samples by heuristically leveraging the memory mechanism of deep neural networks. Then, it aligns those unlabeled data with the training data into a unified feature space by adversarial training to assign pseudo labels and further utilize the information contained in them. Experiments on two wildly-used benchmark datasets demonstrate the effectiveness of our approach.

Fri Oct 30 2020
NLP
Towards Accurate and Consistent Evaluation: A Dataset for Distantly-Supervised Relation Extraction
Distant Supervision (DS) can automatically generate large-scale annotated data by aligning entity pairs from Knowledge Bases to sentences. These DS-generated datasets have wrong labels that result in incorrect evaluation scores. To solve this problem, we build a new dataset NYTH,
0
0
0
Fri May 21 2021
NLP
Revisiting the Negative Data of Distantly Supervised Relation Extraction
Distantly supervision automatically generates plenty of training samples for relation extraction. However, it also incurs two major problems: noisy labels and imbalanced training data. Previous works focus more on reducing wrongly labeled relations (false positives) while few explore the missing relations that are caused by incompleteness.
0
0
0
Wed Jun 19 2019
NLP
Fine-tuning Pre-Trained Transformer Language Models to Distantly Supervised Relation Extraction
Distantly supervised relation extraction is widely used to extract relational facts from text. Current relation extraction methods try to alleviate the noise by multi-instance learning. While achieving state-of-the-art results, we observed models to be biased towards recognizing a limited set of relations with high precision.
0
0
0
Tue Dec 11 2018
NLP
RESIDE: Improving Distantly-Supervised Neural Relation Extraction using Side Information
Distantly-supervised Relation Extraction (RE) methods train an extractor by automatically aligning relation instances in a Knowledge Base (KB) with unstructured text. KBs often contain other side information, such as aliases of relations (e.g., founded and
0
0
0
Fri Nov 15 2019
Machine Learning
Improving Distant Supervised Relation Extraction by Dynamic Neural Network
Distant Supervised Relation Extraction (DSRE) is usually formulated as a problem of classifying a bag of sentences that contain two query entities. Most existing methods consider those relation classes as distinct semantic categories while ignoring their potential connection to query entity types.
0
0
0
Thu Sep 12 2019
NLP
Uncover the Ground-Truth Relations in Distant Supervision: A Neural Expectation-Maximization Framework
Distant supervision for relation extraction enables one to effectively acquire structured relations out of very large text corpora with less human efforts. Most of the prior-art models for such tasks assume that the given text can be noisy, but their corresponding labels are clean.
0
0
0
Tue Jun 10 2014
Machine Learning
Generative Adversarial Networks
We propose a new framework for estimating generative models via an adversarial process. We simultaneously train two models: a generative model G that captures the data distribution, and a discriminative model D. The training procedure for G is to maximize the probability of D making a mistake.
9
3,421
23,915
Mon Jun 12 2017
NLP
Attention Is All You Need
The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms. Experiments on two machine translation tasks show these models to be superior in
50
215
883
Fri Apr 16 2021
NLP
Distantly Supervised Relation Extraction with Sentence Reconstruction and Knowledge Base Priors
We propose a multi-task, probabilistic approach to facilitate distantlysupervised relation extraction. We bias the latent space of sentences via a Variational Autoencoder (VAE) that is trained jointly with a relation classifier.
2
3
17
Thu Oct 11 2018
NLP
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
BERT is designed to pre-train deep                bidirectional representations from unlabeled text. It can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks.
14
8
15
Mon Sep 01 2014
NLP
Neural Machine Translation by Jointly Learning to Align and Translate
Neural machine translation is a recently proposed approach to machine translation. Unlike traditional statistical machine translation, the neural machine translation aims at building a single neural network that can be tuned to maximize translation performance.
6
4
7
Thu Jul 16 2020
Machine Learning
Learning from Noisy Labels with Deep Neural Networks: A Survey
Deep learning has achieved remarkable success in numerous domains with help from large amounts of big data. The quality of data labels is a Concern because of the lack of high-quality labels in many real-world scenarios. As noisy labels severely degrade the generalization performance of deep neural networks, learning from
1
0
1