Year: 2020
Type: conference-paper
Abstract: Document-level relation extraction aims to extract relations among entities within a document.Different from sentence-level relation extraction, it requires reasoning over multiple sentences across paragraphs.In this paper, we propose Graph Aggregation-and-Inference Network (GAIN), a method to recognize such relations for long paragraphs.GAIN constructs two graphs, a heterogeneous mentionlevel graph (MG) and an entity-level graph (EG).The former captures complex interaction among different mentions and the latter aggregates mentions underlying for the same entities.Based on the graphs we propose a novel path reasoning mechanism to infer relations between entities.Experiments on the public dataset, DocRED, show GAIN achieves a significant performance improvement (2.85 on F1) over the previous state-of-the-art.Our code is available at https://github.com/ PKUnlp-icler/GAIN.
Authors: Shuang Zeng, Runxin Xu, Baobao Chang, Lei Li
Institutions: Peking University, ByteDance (China)
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Awards: G138806403, 基于语言认知机理的汉语框架语义计算研究
OpenAlex ID: W3103836967