{"type":"ScholarlyArticle","title":"Document-level Relation Extraction as Semantic Segmentation","authors":[{"name":"Ningyu Zhang","slug":"ningyu-zhang","given":"Ningyu","family":"Zhang","affiliation":""},{"name":"Xiang Chen","slug":"xiang-chen","given":"Xiang","family":"Chen","affiliation":""},{"name":"Xin Xie","slug":"xin-xie","given":"Xin","family":"Xie","affiliation":""},{"name":"Shumin Deng","slug":"shumin-deng","given":"Shumin","family":"Deng","affiliation":""},{"name":"Chuanqi Tan","slug":"chuanqi-tan","given":"Chuanqi","family":"Tan","affiliation":""},{"name":"Mosha Chen","slug":"mosha-chen","given":"Mosha","family":"Chen","affiliation":""},{"name":"Fei Huang","slug":"fei-huang","given":"Fei","family":"Huang","affiliation":""},{"name":"Luo Si","slug":"luo-si","given":"Luo","family":"Si","affiliation":""},{"name":"Huajun Chen","slug":"huajun-chen","given":"Huajun","family":"Chen","affiliation":""}],"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.","doi":"10.24963/ijcai.2021/551","url":"https://ijcai.org/proceedings/2021/551","pdf":"https://ijcai.org/proceedings/2021/0551.pdf","markdown":"https://ijcai.org/proceedings/2021/551.md","bibtex":"https://ijcai.org/proceedings/2021/bibtex/551","volume":{"slug":"2021","title":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2021","url":"https://ijcai.org/proceedings/2021/","year":2021,"location":"Montreal","dates":"19-27 August 2021","editors":"Prof. Zhi-Hua Zhou","isbn":"978-0-9992411-9-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2021"},"section":"Natural Language Processing","track":"Main Track","number":551,"pages":{"first":3999,"last":4006},"keywords":["Natural Language Processing: Information Extraction","Natural Language Processing: Knowledge Extraction"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}