mlsanityData to 7 Oct 2026

De-biasing Distantly Supervised Named Entity Recognition via Causal Intervention

arXiv 2106.09233 ↗First posted 17 Jun 2021cs.CLcited by 24

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). Builds on 13 of its 35 references that are in the map. First posted on arXiv 17 Jun 2021.

Builds on

13 of 35 references.

References · 13

  1. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  2. 2016Neural Architectures for Named Entity Recognitioncited by 548
  3. 2018AllenNLP: A Deep Semantic Natural Language Processing Platformcited by 347
  4. 2016End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRFcited by 341
  5. 2020Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effectcited by 256
  6. 2020Representation Learning via Invariant Causal Mechanismscited by 197
  7. 2015Large-scale Simple Question Answering with Memory Networkscited by 127
  8. 2020BOND: BERT-Assisted Open-Domain Named Entity Recognition with Distant Supervisioncited by 91
  9. 2019Two Causal Principles for Improving Visual Dialogcited by 75
  10. 2018Learning Named Entity Tagger using Domain-Specific Dictionarycited by 65
  11. 2019Distantly Supervised Named Entity Recognition using Positive-Unlabeled Learningcited by 46
  12. 2019Sequence-to-Nuggets: Nested Entity Mention Detection via Anchor-Region Networkscited by 33
1 more
  1. 2019Low-Resource Name Tagging Learned with Weakly Labeled Datacited by 32

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 7; 2023: 6; 2024: 6; 2025: 3.

24 papers.

Sort:

By area:

  1. 2023Context De-confounded Emotion Recognitioncited by 34
  2. 2022Optimizing Bi-Encoder for Named Entity Recognition via Contrastive Learningcited by 24
  3. 2021Fine-grained Entity Typing via Label Reasoningcited by 22
  4. 2022Distantly Supervised Named Entity Recognition via Confidence-Based Multi-Class Positive and Unlabeled Learningcited by 21
  5. 2022Few-shot Named Entity Recognition with Self-describing Networkscited by 16
  6. 2022Does Your Model Classify Entities Reasonably? Diagnosing and Mitigating Spurious Correlations in Entity Typingcited by 16
  7. 2023Preserving Commonsense Knowledge from Pre-trained Language Models via Causal Inferencecited by 13
  8. 2024Towards Context-Aware Emotion Recognition Debiasing from a Causal Demystification Perspective via De-confounded Trainingcited by 11
  9. 2022Distilling Causal Effect from Miscellaneous Other-Class for Continual Named Entity Recognitioncited by 10
  10. 2024Debiased Multimodal Understanding for Human Language Sequencescited by 10
  11. 2021Honey or Poison? Solving the Trigger Curse in Few-shot Event Detection via Causal Interventioncited by 9
  12. 2022Debiasing Stance Detection Models with Counterfactual Reasoning and Adversarial Bias Learningcited by 5
12 more
  1. 2023MProto: Multi-Prototype Network with Denoised Optimal Transport for Distantly Supervised Named Entity Recognitioncited by 4
  2. 2023PromptORE -- A Novel Approach Towards Fully Unsupervised Relation Extractioncited by 3
  3. 2024Domain Generalization via Causal Adjustment for Cross-Domain Sentiment Analysiscited by 3
  4. 2024DINER: Debiasing Aspect-based Sentiment Analysis with Multi-variable Causal Inferencecited by 3
  5. 2023Better Sampling of Negatives for Distantly Supervised Named Entity Recognitioncited by 2
  6. 2022Investigating the Robustness of Natural Language Generation from Logical Forms via Counterfactual Samplescited by 1
  7. 2024Balancing the Causal Effects in Class-Incremental Learningcited by 1
  8. 2025Few Dimensions are Enough: Fine-tuning BERT with Selected Dimensions Revealed Its Redundant Naturecited by 1
  9. 2023Causal Interventions-based Few-Shot Named Entity Recognitioncited by 0
  10. 2024Semi-Supervised Learning from Small Annotated Data and Large Unlabeled Data for Fine-grained PICO Entity Recognitioncited by 0
  11. 2025Towards DS-NER: Unveiling and Addressing Latent Noise in Distant Annotationscited by 0
  12. 2025Argument-Centric Causal Intervention Method for Mitigating Bias in Cross-Document Event Coreference Resolutioncited by 0