# Entity and Evidence Guided Relation Extraction for DocRED

arXiv: https://arxiv.org/abs/2008.12283 · HTML: https://mlsanity.com/paper/2008.12283/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Aug 2020.

## Built on by (most cited first, 3 of 3)

- [SAIS: Supervising and Augmenting Intermediate Steps for Document-Level Relation Extraction](https://mlsanity.com/paper/2109.12093/) (2021)
- [DORE: Document Ordered Relation Extraction based on Generative Framework](https://mlsanity.com/paper/2210.16064/) (2022)
- [SpanDrop: Simple and Effective Counterfactual Learning for Long Sequences](https://mlsanity.com/paper/2208.02169/) (2022)

## Abstract (arXiv)

Document-level relation extraction is a challenging task which requires reasoning over multiple sentences in order to predict relations in a document. In this paper, we pro-pose a joint training frameworkE2GRE(Entity and Evidence Guided Relation Extraction)for this task. First, we introduce entity-guided sequences as inputs to a pre-trained language model (e.g. BERT, RoBERTa). These entity-guided sequences help a pre-trained language model (LM) to focus on areas of the document related to the entity. Secondly, we guide the fine-tuning of the pre-trained language model by using its internal attention probabilities as additional features for evidence prediction.Our new approach encourages the pre-trained language model to focus on the entities and supporting/evidence sentences. We evaluate our E2GRE approach on DocRED, a recently released large-scale dataset for relation extraction. Our approach is able to achieve state-of-the-art results on the public leaderboard across all metrics, showing that our E2GRE is both effective and synergistic on relation extraction and evidence prediction.