Denoising Graph Inference Network for Document-Level Relation Extraction

Denoising Graph Inference Network for Document-Level Relation Extraction

Relation Extraction (RE) is to obtain a predefined relation type of two entities mentioned in a piece of text, e.g., a sentence-level or a document-level text. Most existing studies suffer from the noise in the text, and necessary pruning is of great importance. The conventional sentence-level RE ta...

Full description

Bibliographic Details
Main Authors: Hailin Wang, Ke Qin, Guiduo Duan, Guangchun Luo
Format: Article
Language:English
Published: Tsinghua University Press 2023-06-01
Series:Big Data Mining and Analytics
Subjects:
relation eextraction (re)
document-level
denoising
linguistic knowledge
attention mechanism
Online Access:https://www.sciopen.com/article/10.26599/BDMA.2022.9020051

Internet

https://www.sciopen.com/article/10.26599/BDMA.2022.9020051

Similar Items