# Relation Extraction with Explanation

arXiv: https://arxiv.org/abs/2005.14271 · HTML: https://mlsanity.com/paper/2005.14271/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 May 2020.

## Built on by (most cited first, 7 of 7)

- [From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI](https://mlsanity.com/paper/2201.08164/) (2022)
- [What do You Mean by Relation Extraction? A Survey on Datasets and Study on Scientific Relation Classification](https://mlsanity.com/paper/2204.13516/) (2022)
- [How Knowledge Graph and Attention Help? A Quantitative Analysis into Bag-level Relation Extraction](https://mlsanity.com/paper/2107.12064/) (2021)
- [D-REX: Dialogue Relation Extraction with Explanations](https://mlsanity.com/paper/2109.05126/) (2021)
- [SuMe: A Dataset Towards Summarizing Biomedical Mechanisms](https://mlsanity.com/paper/2205.04652/) (2022)
- [Explaining Relation Classification Models with Semantic Extents](https://mlsanity.com/paper/2308.02193/) (2023)
- [The Answer Lies Within: Self-Derived Rewards Enable Explainable Relation Extraction](https://mlsanity.com/paper/2510.06198/) (2025)

## Abstract (arXiv)

Recent neural models for relation extraction with distant supervision alleviate the impact of irrelevant sentences in a bag by learning importance weights for the sentences. Efforts thus far have focused on improving extraction accuracy but little is known about their explainability. In this work we annotate a test set with ground-truth sentence-level explanations to evaluate the quality of explanations afforded by the relation extraction models. We demonstrate that replacing the entity mentions in the sentences with their fine-grained entity types not only enhances extraction accuracy but also improves explanation. We also propose to automatically generate "distractor" sentences to augment the bags and train the model to ignore the distractors. Evaluations on the widely used FB-NYT dataset show that our methods achieve new state-of-the-art accuracy while improving model explainability.