Distantly-Supervised Named Entity Recognition with Noise-Robust Learning and Language Model Augmented Self-Training

09/10/2021
by   Yu Meng, et al.
0

We study the problem of training named entity recognition (NER) models using only distantly-labeled data, which can be automatically obtained by matching entity mentions in the raw text with entity types in a knowledge base. The biggest challenge of distantly-supervised NER is that the distant supervision may induce incomplete and noisy labels, rendering the straightforward application of supervised learning ineffective. In this paper, we propose (1) a noise-robust learning scheme comprised of a new loss function and a noisy label removal step, for training NER models on distantly-labeled data, and (2) a self-training method that uses contextualized augmentations created by pre-trained language models to improve the generalization ability of the NER model. On three benchmark datasets, our method achieves superior performance, outperforming existing distantly-supervised NER models by significant margins.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/28/2020

BOND: BERT-Assisted Open-Domain Named Entity Recognition with Distant Supervision

We study the open-domain named entity recognition (NER) problem under di...
research
12/29/2020

Few-Shot Named Entity Recognition: A Comprehensive Study

This paper presents a comprehensive study to efficiently build named ent...
research
05/22/2023

Better Sampling of Negatives for Distantly Supervised Named Entity Recognition

Distantly supervised named entity recognition (DS-NER) has been proposed...
research
10/09/2021

Improving Distantly-Supervised Named Entity Recognition with Self-Collaborative Denoising Learning

Distantly supervised named entity recognition (DS-NER) efficiently reduc...
research
06/17/2021

Denoising Distantly Supervised Named Entity Recognition via a Hypergeometric Probabilistic Model

Denoising is the essential step for distant supervision based named enti...
research
12/13/2022

Distantly-Supervised Named Entity Recognition with Adaptive Teacher Learning and Fine-grained Student Ensemble

Distantly-Supervised Named Entity Recognition (DS-NER) effectively allev...
research
05/04/2019

Learning to Denoise Distantly-Labeled Data for Entity Typing

Distantly-labeled data can be used to scale up training of statistical m...

Please sign up or login with your details

Forgot password? Click here to reset