# Coarse-to-Fine Entity Representations for Document-level Relation Extraction

arXiv: https://arxiv.org/abs/2012.02507 · HTML: https://mlsanity.com/paper/2012.02507/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Dec 2020.

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

- [SIRE: Separate Intra- and Inter-sentential Reasoning for Document-level Relation Extraction](https://mlsanity.com/paper/2106.01709/) (2021)
- [None Class Ranking Loss for Document-Level Relation Extraction](https://mlsanity.com/paper/2205.00476/) (2022)
- [Incorporating Connections Beyond Knowledge Embeddings: A Plug-and-Play Module to Enhance Commonsense Reasoning in Machine Reading Comprehension](https://mlsanity.com/paper/2103.14443/) (2021)

## Abstract (arXiv)

Document-level Relation Extraction (RE) requires extracting relations expressed within and across sentences. Recent works show that graph-based methods, usually constructing a document-level graph that captures document-aware interactions, can obtain useful entity representations thus helping tackle document-level RE. These methods either focus more on the entire graph, or pay more attention to a part of the graph, e.g., paths between the target entity pair. However, we find that document-level RE may benefit from focusing on both of them simultaneously. Therefore, to obtain more comprehensive entity representations, we propose the Coarse-to-Fine Entity Representation model (CFER) that adopts a coarse-to-fine strategy involving two phases. First, CFER uses graph neural networks to integrate global information in the entire graph at a coarse level. Next, CFER utilizes the global information as a guidance to selectively aggregate path information between the target entity pair at a fine level. In classification, we combine the entity representations from both two levels into more comprehensive representations for relation extraction. Experimental results on two document-level RE datasets, DocRED and CDR, show that CFER outperforms existing models and is robust to the uneven label distribution.