# Element Intervention for Open Relation Extraction

arXiv: https://arxiv.org/abs/2106.09558 · HTML: https://mlsanity.com/paper/2106.09558/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 40 references that are in the map.
- First posted on arXiv 17 Jun 2021.

## Builds on (most cited first, 15 of 15)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Annotation Artifacts in Natural Language Inference Data](https://mlsanity.com/paper/1803.02324/) (2018)
- [Matching the Blanks: Distributional Similarity for Relation Learning](https://mlsanity.com/paper/1906.03158/) (2019)
- [Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect](https://mlsanity.com/paper/2009.12991/) (2020)
- [FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation](https://mlsanity.com/paper/1810.10147/) (2018)
- [Pathologies of Neural Models Make Interpretations Difficult](https://mlsanity.com/paper/1804.07781/) (2018)
- [Investigating Pretrained Language Models for Graph-to-Text Generation](https://mlsanity.com/paper/2007.08426/) (2020)
- [Two Causal Principles for Improving Visual Dialog](https://mlsanity.com/paper/1911.10496/) (2019)
- [Learning from Context or Names? An Empirical Study on Neural Relation Extraction](https://mlsanity.com/paper/2010.01923/) (2020)
- [Back to the Future: Unsupervised Backprop-based Decoding for Counterfactual and Abductive Commonsense Reasoning](https://mlsanity.com/paper/2010.05906/) (2020)
- [SelfORE: Self-supervised Relational Feature Learning for Open Relation Extraction](https://mlsanity.com/paper/2004.02438/) (2020)
- [SSCR: Iterative Language-Based Image Editing via Self-Supervised Counterfactual Reasoning](https://mlsanity.com/paper/2009.09566/) (2020)

## Built on by (most cited first, 11 of 11)

- [HiURE: Hierarchical Exemplar Contrastive Learning for Unsupervised Relation Extraction](https://mlsanity.com/paper/2205.02225/) (2022)
- [Open Relation and Event Type Discovery with Type Abstraction](https://mlsanity.com/paper/2212.00178/) (2022)
- [Improving Unsupervised Relation Extraction by Augmenting Diverse Sentence Pairs](https://mlsanity.com/paper/2312.00552/) (2023)
- [Honey or Poison? Solving the Trigger Curse in Few-shot Event Detection via Causal Intervention](https://mlsanity.com/paper/2109.05747/) (2021)
- [Pre-training to Match for Unified Low-shot Relation Extraction](https://mlsanity.com/paper/2203.12274/) (2022)
- [A Survey on Open Information Extraction from Rule-based Model to Large Language Model](https://mlsanity.com/paper/2208.08690/) (2022)
- [PromptORE -- A Novel Approach Towards Fully Unsupervised Relation Extraction](https://mlsanity.com/paper/2304.01209/) (2023)
- [Learning from Semi-Factuals: A Debiased and Semantic-Aware Framework for Generalized Relation Discovery](https://mlsanity.com/paper/2401.06327/) (2024)
- [Siamese Representation Learning for Unsupervised Relation Extraction](https://mlsanity.com/paper/2310.00552/) (2023)
- [Towards a More Generalized Approach in Open Relation Extraction](https://mlsanity.com/paper/2505.22801/) (2025)
- [Causal Interventions-based Few-Shot Named Entity Recognition](https://mlsanity.com/paper/2305.01914/) (2023)

## Abstract (arXiv)

Open relation extraction aims to cluster relation instances referring to the same underlying relation, which is a critical step for general relation extraction. Current OpenRE models are commonly trained on the datasets generated from distant supervision, which often results in instability and makes the model easily collapsed. In this paper, we revisit the procedure of OpenRE from a causal view. By formulating OpenRE using a structural causal model, we identify that the above-mentioned problems stem from the spurious correlations from entities and context to the relation type. To address this issue, we conduct Element Intervention, which intervenes on the context and entities respectively to obtain the underlying causal effects of them. We also provide two specific implementations of the interventions based on entity ranking and context contrasting. Experimental results on unsupervised relation extraction datasets show that our methods outperform previous state-of-the-art methods and are robust across different datasets.