De-biasing Distantly Supervised Named Entity Recognition via Causal Intervention

by   Wenkai Zhang, et al.

Distant supervision tackles the data bottleneck in NER by automatically generating training instances via dictionary matching. Unfortunately, the learning of DS-NER is severely dictionary-biased, which suffers from spurious correlations and therefore undermines the effectiveness and the robustness of the learned models. In this paper, we fundamentally explain the dictionary bias via a Structural Causal Model (SCM), categorize the bias into intra-dictionary and inter-dictionary biases, and identify their causes. Based on the SCM, we learn de-biased DS-NER via causal interventions. For intra-dictionary bias, we conduct backdoor adjustment to remove the spurious correlations introduced by the dictionary confounder. For inter-dictionary bias, we propose a causal invariance regularizer which will make DS-NER models more robust to the perturbation of dictionaries. Experiments on four datasets and three DS-NER models show that our method can significantly improve the performance of DS-NER.


page 1

page 2

page 3

page 4


HAMNER: Headword Amplified Multi-span Distantly Supervised Method for Domain Specific Named Entity Recognition

To tackle Named Entity Recognition (NER) tasks, supervised methods need ...

Causal Interventions-based Few-Shot Named Entity Recognition

Few-shot named entity recognition (NER) systems aims at recognizing new ...

Learning Named Entity Tagger using Domain-Specific Dictionary

Recent advances in deep neural models allow us to build reliable named e...

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

Distantly-Supervised Named Entity Recognition (DS-NER) effectively allev...

A Comprehensive Study of Gender Bias in Chemical Named Entity Recognition Models

Objective. Chemical named entity recognition (NER) models have the poten...

Distilling Causal Effect from Miscellaneous Other-Class for Continual Named Entity Recognition

Continual Learning for Named Entity Recognition (CL-NER) aims to learn a...

Reducing Bias in Modeling Real-world Password Strength via Deep Learning and Dynamic Dictionaries

Password security hinges on an accurate understanding of the techniques ...

Please sign up or login with your details

Forgot password? Click here to reset