Large Model并行优化为什么要并行优化?大就是好, 虽然丛2019年人们的认识普遍就是大就是好, 这个概念在当今依然没有被改变, 只是有了更深刻的认识. 所以, 为什么要并行? 虽然大就是好, 模型太大显存吃不消(空间)

Query-based Instance Discrimination Network for Relational Triple Extraction本文是论文Query-based Instance Discrimination Net

UniRel: Unified Representation and Interaction for Joint Relational Triple Extraction本文是论文UniRel: Unified Representation

OneEE: A One-Stage Framework for Fast Overlapping and Nested Event Extraction本文是论文OneEE: A One-Stage Framework for Fast

W2NER: Unified Named Entity Recognition as Word - Word Relation Classification本文是论文Unified Named Entity Recognition as W

UniRE: A Unified Label Space for Entity Relation Extraction本文是论文UniRE: A Unified Label Space for Entity Relation Extract

Relational Triple Extraction: One Step is Enough本文是论文Relational Triple Extraction: One Step is Enough 的阅读笔记和个人理解, 论文来自IJ

本文前置知识: TPLinker: TPLinker: Single-stage Joint Extraction of Entities and Relations Through Token Pair Linking. OneR

Pytorch学习: Pytorch LightningPytorch Lightning是在Pytorch基础上封装的框架, 号称”Pytorch里的Keras”, 如官网所述, 它具有灵活, 解耦, 易于复现, 自动化, 扩展性好等优点

本文前置知识: SPN: SPN: Joint Entity and Relation Extraction with Set Prediction Networks. RFBFN: A Relation - First Blank

Joint Entity and Relation Extraction with Set Prediction Networks本文是论文Joint Entity and Relation Extraction with Set Pred

本文前置知识: CasRel: 详见CasRel: A Novel Cascade Binary Tagging Framework for Relational Triple Extraction. TPLinker: 详见TPLin