MKDAT: Multi-Level Knowledge Distillation with Adaptive Temperature for Distantly Supervised Relation Extraction

MKDAT: Multi-Level Knowledge Distillation with Adaptive Temperature for Distantly Supervised Relation Extraction

Distantly supervised relation extraction (DSRE), first used to address the limitations of manually annotated data via automatically annotating the data with triplet facts, is prone to issues such as mislabeled annotations due to the interference of noisy annotations. To address the interference of n...

Full description

Bibliographic Details
Main Authors: Jun Long, Zhuoying Yin, Yan Han, Wenti Huang
Format: Article
Language:English
Published: MDPI AG 2024-06-01
Series:Information
Subjects:
distantly supervised relation extraction
knowledge distillation
label softening
Online Access:https://www.mdpi.com/2078-2489/15/7/382

Internet

https://www.mdpi.com/2078-2489/15/7/382

Similar Items