---
title: "Document-level Relation Extraction as Semantic Segmentation"
authors:
  - "Ningyu Zhang"
  - "Xiang Chen"
  - "Xin Xie"
  - "Shumin Deng"
  - "Chuanqi Tan"
  - "Mosha Chen"
  - "Fei Huang"
  - "Luo Si"
  - "Huajun Chen"
doi: "10.24963/ijcai.2021/551"
url: "https://ijcai.org/proceedings/2021/551"
pdf: "https://ijcai.org/proceedings/2021/0551.pdf"
venue: "Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence"
year: 2021
pages: "3999-4006"
track: "Main Track"
keywords:
  - "Natural Language Processing: Information Extraction"
  - "Natural Language Processing: Knowledge Extraction"
---

# Document-level Relation Extraction as Semantic Segmentation

Ningyu Zhang, Xiang Chen, Xin Xie, Shumin Deng, Chuanqi Tan, Mosha Chen, Fei Huang, Luo Si, Huajun Chen

*Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence*, pages 3999-4006. DOI: [10.24963/ijcai.2021/551](https://doi.org/10.24963/ijcai.2021/551)

## Abstract

Document-level relation extraction aims to extract relations among multiple entity pairs from a document. Previously proposed graph-based or transformer-based models utilize the entities independently, regardless of global information among relational triples. This paper approaches the problem by predicting an entity-level relation matrix to capture local and global information, parallel to the semantic segmentation task in computer vision. Herein, we propose a Document U-shaped Network for document-level relation extraction. Specifically, we leverage an encoder module to capture the context information of entities and a U-shaped segmentation module over the image-style feature map to capture global interdependency among triples. Experimental results show that our approach can obtain state-of-the-art performance on three benchmark datasets DocRED, CDR, and GDA.