DaNing
通用信息抽取(下) - UniEX, Mirror, RexUIE 通用信息抽取(下) - UniEX, Mirror, RexUIE
本文前置知识: 通用信息抽取(上) - UIE, USM, InstructUIE. 通用信息抽取(下) - UniEX, Mirror, RexUIE本文为介绍通用信息抽取领域经典模型的下篇, 将会介绍了UniEX, Mirror
2024-05-29
通用信息抽取(上) - UIE, USM, InstructUIE 通用信息抽取(上) - UIE, USM, InstructUIE
2024.5.27: 稍微补充了UIE的其中一个改进版MetaRetriever. 本文前置知识: T5: Exploring the Limits of Transfer Learning with a Unified Text-to
2024-01-21
Vision & Language Pretrained Model 总结 Vision & Language Pretrained Model 总结
2024.4.21: 添加CoCa, 并修改对WPA的描述. 2024.4.23: 增加了BLIP-2的部分描述. Vision & Language Pretraining 总结本文只是以总结的形式梳理了近期比较有代表性的VL
2023-07-18
Large Model并行优化 Large Model并行优化
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)
2023-06-01
QIDN: Query-based Instance Discrimination Network for Relational Triple Extraction QIDN: Query-based Instance Discrimination Network for Relational Triple Extraction
Query-based Instance Discrimination Network for Relational Triple Extraction本文是论文Query-based Instance Discrimination Net
2023-02-10
UniRel: Unified Representation and Interaction for Joint Relational Triple Extraction UniRel: Unified Representation and Interaction for Joint Relational Triple Extraction
UniRel: Unified Representation and Interaction for Joint Relational Triple Extraction本文是论文UniRel: Unified Representation
2023-01-03
OneEE: A One-Stage Framework for Fast Overlapping and Nested Event Extraction OneEE: A One-Stage Framework for Fast Overlapping and Nested Event Extraction
OneEE: A One-Stage Framework for Fast Overlapping and Nested Event Extraction本文是论文OneEE: A One-Stage Framework for Fast
2022-11-21
W2NER: Unified Named Entity Recognition as Word - Word Relation Classification W2NER: Unified Named Entity Recognition as Word - Word Relation Classification
W2NER: Unified Named Entity Recognition as Word - Word Relation Classification本文是论文Unified Named Entity Recognition as W
2022-10-16
UniRE: A Unified Label Space for Entity Relation Extraction UniRE: A Unified Label Space for Entity Relation Extraction
UniRE: A Unified Label Space for Entity Relation Extraction本文是论文UniRE: A Unified Label Space for Entity Relation Extract
2022-09-22
DirectRel: Relational Triple Extraction - One Step is Enough DirectRel: Relational Triple Extraction - One Step is Enough
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
2022-08-31
OneRel: Joint Entity and Relation Extraction with One Module in One Step OneRel: Joint Entity and Relation Extraction with One Module in One Step
本文前置知识: TPLinker: TPLinker: Single-stage Joint Extraction of Entities and Relations Through Token Pair Linking. OneR
2022-08-14
Pytorch学习: Pytorch Lightning Pytorch学习: Pytorch Lightning
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
2022-08-14
1 / 5