# Learning from Context or Names? An Empirical Study on Neural Relation Extraction

arXiv: https://arxiv.org/abs/2010.01923 · HTML: https://mlsanity.com/paper/2010.01923/

## Key facts

- Cited by 75 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Oct 2020.

## Built on by (most cited first, 30 of 75)

- [PTR: Prompt Tuning with Rules for Text Classification](https://mlsanity.com/paper/2105.11259/) (2021)
- [An Improved Baseline for Sentence-level Relation Extraction](https://mlsanity.com/paper/2102.01373/) (2021)
- [Prompt-Learning for Fine-Grained Entity Typing](https://mlsanity.com/paper/2108.10604/) (2021)
- [Document-Level Relation Extraction with Adaptive Focal Loss and Knowledge Distillation](https://mlsanity.com/paper/2203.10900/) (2022)
- [CLEVE: Contrastive Pre-training for Event Extraction](https://mlsanity.com/paper/2105.14485/) (2021)
- [HiURE: Hierarchical Exemplar Contrastive Learning for Unsupervised Relation Extraction](https://mlsanity.com/paper/2205.02225/) (2022)
- [Summarization as Indirect Supervision for Relation Extraction](https://mlsanity.com/paper/2205.09837/) (2022)
- [Should We Rely on Entity Mentions for Relation Extraction? Debiasing Relation Extraction with Counterfactual Analysis](https://mlsanity.com/paper/2205.03784/) (2022)
- [Modality-Aware Contrastive Instance Learning with Self-Distillation for Weakly-Supervised Audio-Visual Violence Detection](https://mlsanity.com/paper/2207.05500/) (2022)
- [Context versus Prior Knowledge in Language Models](https://mlsanity.com/paper/2404.04633/) (2024)
- [Exploring Task Difficulty for Few-Shot Relation Extraction](https://mlsanity.com/paper/2109.05473/) (2021)
- [SAIS: Supervising and Augmenting Intermediate Steps for Document-Level Relation Extraction](https://mlsanity.com/paper/2109.12093/) (2021)
- [Uncovering Main Causalities for Long-tailed Information Extraction](https://mlsanity.com/paper/2109.05213/) (2021)
- [A Causal View of Entity Bias in (Large) Language Models](https://mlsanity.com/paper/2305.14695/) (2023)
- [SLANG: New Concept Comprehension of Large Language Models](https://mlsanity.com/paper/2401.12585/) (2024)
- [Unified Semantic Typing with Meaningful Label Inference](https://mlsanity.com/paper/2205.01826/) (2022)
- [REFinD: Relation Extraction Financial Dataset](https://mlsanity.com/paper/2305.18322/) (2023)
- [MapRE: An Effective Semantic Mapping Approach for Low-resource Relation Extraction](https://mlsanity.com/paper/2109.04108/) (2021)
- [TAGPRIME: A Unified Framework for Relational Structure Extraction](https://mlsanity.com/paper/2205.12585/) (2022)
- [CIL: Contrastive Instance Learning Framework for Distantly Supervised Relation Extraction](https://mlsanity.com/paper/2106.10855/) (2021)
- [Learning Robust Representations for Continual Relation Extraction via Adversarial Class Augmentation](https://mlsanity.com/paper/2210.04497/) (2022)
- [Can NLI Provide Proper Indirect Supervision for Low-resource Biomedical Relation Extraction?](https://mlsanity.com/paper/2212.10784/) (2022)
- [Meta In-Context Learning Makes Large Language Models Better Zero and Few-Shot Relation Extractors](https://mlsanity.com/paper/2404.17807/) (2024)
- [Manual Evaluation Matters: Reviewing Test Protocols of Distantly Supervised Relation Extraction](https://mlsanity.com/paper/2105.09543/) (2021)
- [Element Intervention for Open Relation Extraction](https://mlsanity.com/paper/2106.09558/) (2021)
- [Can Transformers Capture Spatial Relations between Objects?](https://mlsanity.com/paper/2403.00729/) (2024)
- [Improving BERT Model Using Contrastive Learning for Biomedical Relation Extraction](https://mlsanity.com/paper/2104.13913/) (2021)
- [GDA: Generative Data Augmentation Techniques for Relation Extraction Tasks](https://mlsanity.com/paper/2305.16663/) (2023)
- [Distantly-Supervised Long-Tailed Relation Extraction Using Constraint Graphs](https://mlsanity.com/paper/2105.11225/) (2021)
- [A Simple yet Effective Relation Information Guided Approach for Few-Shot Relation Extraction](https://mlsanity.com/paper/2205.09536/) (2022)

## Abstract (arXiv)

Neural models have achieved remarkable success on relation extraction (RE) benchmarks. However, there is no clear understanding which type of information affects existing RE models to make decisions and how to further improve the performance of these models. To this end, we empirically study the effect of two main information sources in text: textual context and entity mentions (names). We find that (i) while context is the main source to support the predictions, RE models also heavily rely on the information from entity mentions, most of which is type information, and (ii) existing datasets may leak shallow heuristics via entity mentions and thus contribute to the high performance on RE benchmarks. Based on the analyses, we propose an entity-masked contrastive pre-training framework for RE to gain a deeper understanding on both textual context and type information while avoiding rote memorization of entities or use of superficial cues in mentions. We carry out extensive experiments to support our views, and show that our framework can improve the effectiveness and robustness of neural models in different RE scenarios. All the code and datasets are released at https://github.com/thunlp/RE-Context-or-Names.