SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2009.13752 · EMNLP · 2020

Double Graph Based Reasoning for Document-level Relation Extraction

Lei Li, Baobao Chang, Shuang Zeng, Runxin Xu, Elias Brown

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2009.13752")
get_code_for_paper("2009.13752")
have("2009.13752")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2009.13752.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2009.13752.svg)](https://syntology.ai/paper/2009.13752)

Connect an agent — have() is free.