# De-biasing Distantly Supervised Named Entity Recognition via Causal Intervention

arXiv: https://arxiv.org/abs/2106.09233 · HTML: https://mlsanity.com/paper/2106.09233/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 35 references that are in the map.
- First posted on arXiv 17 Jun 2021.

## Builds on (most cited first, 13 of 13)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Neural Architectures for Named Entity Recognition](https://mlsanity.com/paper/1603.01360/) (2016)
- [AllenNLP: A Deep Semantic Natural Language Processing Platform](https://mlsanity.com/paper/1803.07640/) (2018)
- [End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF](https://mlsanity.com/paper/1603.01354/) (2016)
- [Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect](https://mlsanity.com/paper/2009.12991/) (2020)
- [Representation Learning via Invariant Causal Mechanisms](https://mlsanity.com/paper/2010.07922/) (2020)
- [Large-scale Simple Question Answering with Memory Networks](https://mlsanity.com/paper/1506.02075/) (2015)
- [BOND: BERT-Assisted Open-Domain Named Entity Recognition with Distant Supervision](https://mlsanity.com/paper/2006.15509/) (2020)
- [Two Causal Principles for Improving Visual Dialog](https://mlsanity.com/paper/1911.10496/) (2019)
- [Learning Named Entity Tagger using Domain-Specific Dictionary](https://mlsanity.com/paper/1809.03599/) (2018)
- [Distantly Supervised Named Entity Recognition using Positive-Unlabeled Learning](https://mlsanity.com/paper/1906.01378/) (2019)
- [Sequence-to-Nuggets: Nested Entity Mention Detection via Anchor-Region Networks](https://mlsanity.com/paper/1906.03783/) (2019)
- [Low-Resource Name Tagging Learned with Weakly Labeled Data](https://mlsanity.com/paper/1908.09659/) (2019)

## Built on by (most cited first, 24 of 24)

- [Context De-confounded Emotion Recognition](https://mlsanity.com/paper/2303.11921/) (2023)
- [Optimizing Bi-Encoder for Named Entity Recognition via Contrastive Learning](https://mlsanity.com/paper/2208.14565/) (2022)
- [Fine-grained Entity Typing via Label Reasoning](https://mlsanity.com/paper/2109.05744/) (2021)
- [Distantly Supervised Named Entity Recognition via Confidence-Based Multi-Class Positive and Unlabeled Learning](https://mlsanity.com/paper/2204.09589/) (2022)
- [Few-shot Named Entity Recognition with Self-describing Networks](https://mlsanity.com/paper/2203.12252/) (2022)
- [Does Your Model Classify Entities Reasonably? Diagnosing and Mitigating Spurious Correlations in Entity Typing](https://mlsanity.com/paper/2205.12640/) (2022)
- [Preserving Commonsense Knowledge from Pre-trained Language Models via Causal Inference](https://mlsanity.com/paper/2306.10790/) (2023)
- [Towards Context-Aware Emotion Recognition Debiasing from a Causal Demystification Perspective via De-confounded Training](https://mlsanity.com/paper/2407.04963/) (2024)
- [Distilling Causal Effect from Miscellaneous Other-Class for Continual Named Entity Recognition](https://mlsanity.com/paper/2210.03980/) (2022)
- [Debiased Multimodal Understanding for Human Language Sequences](https://mlsanity.com/paper/2403.05025/) (2024)
- [Honey or Poison? Solving the Trigger Curse in Few-shot Event Detection via Causal Intervention](https://mlsanity.com/paper/2109.05747/) (2021)
- [Debiasing Stance Detection Models with Counterfactual Reasoning and Adversarial Bias Learning](https://mlsanity.com/paper/2212.10392/) (2022)
- [MProto: Multi-Prototype Network with Denoised Optimal Transport for Distantly Supervised Named Entity Recognition](https://mlsanity.com/paper/2310.08298/) (2023)
- [PromptORE -- A Novel Approach Towards Fully Unsupervised Relation Extraction](https://mlsanity.com/paper/2304.01209/) (2023)
- [Domain Generalization via Causal Adjustment for Cross-Domain Sentiment Analysis](https://mlsanity.com/paper/2402.14536/) (2024)
- [DINER: Debiasing Aspect-based Sentiment Analysis with Multi-variable Causal Inference](https://mlsanity.com/paper/2403.01166/) (2024)
- [Better Sampling of Negatives for Distantly Supervised Named Entity Recognition](https://mlsanity.com/paper/2305.13142/) (2023)
- [Investigating the Robustness of Natural Language Generation from Logical Forms via Counterfactual Samples](https://mlsanity.com/paper/2210.08548/) (2022)
- [Balancing the Causal Effects in Class-Incremental Learning](https://mlsanity.com/paper/2402.10063/) (2024)
- [Few Dimensions are Enough: Fine-tuning BERT with Selected Dimensions Revealed Its Redundant Nature](https://mlsanity.com/paper/2504.04966/) (2025)
- [Causal Interventions-based Few-Shot Named Entity Recognition](https://mlsanity.com/paper/2305.01914/) (2023)
- [Semi-Supervised Learning from Small Annotated Data and Large Unlabeled Data for Fine-grained PICO Entity Recognition](https://mlsanity.com/paper/2412.19346/) (2024)
- [Towards DS-NER: Unveiling and Addressing Latent Noise in Distant Annotations](https://mlsanity.com/paper/2505.12454/) (2025)
- [Argument-Centric Causal Intervention Method for Mitigating Bias in Cross-Document Event Coreference Resolution](https://mlsanity.com/paper/2506.01488/) (2025)

## 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.