(转)格局打开,带你解锁 prompt 的花式用法
(转)美团商品知识图谱的构建及应用
R-Drop-Regularized Dropout for Neural Networks
ConSERT-A Contrastive Framework for Self-Supervised Sentence Representation Transfer
Lexicon Enhanced Chinese Sequence Labelling Using BERT Adapter
(转)对比学习(Contrastive Learning):研究进展精要
An Analysis of Simple Data Augmentation for Named Entity Recognition
FixMatch:Simplifying Semi-Supervised Learning with Consistency and Confidence
StructBERT-Incorporating Languages structures into pre-training for deep language understading
NLP领域有哪些国际顶级会议?
On Layer Normalization in the Transformer Architecture
美团搜索中NER技术的探索与实践
MobileBERT-a Compact Task-Agnostic BERT for Resource-Limited Devices
Boundary Enhanced Neural Span Classification for Nested Named Entity Recognition
聊聊工业界中如何求解NER问题
产品级深度学习系统入门指南
地理文本处理技术在高德的演进
(转)组建技术团队的一些思考
利用 GitHub+Actions 自动部署 Hexo 博客
Fine-Tuning Pretrained Language Models ,Weight Initializations, Data Orders, and Early
NEZHA-Neural Contextualized Representation for Chinese Language Understanding
pip下载python包,离线安装
ALBERT-A Lite BERT For Self-Supervised Learning Of Language Representations
2019达观杯信息提取第九名方案
Lookahead Optimizer k steps forward, 1 step back
RoBERTa-A Robustly Optimized BERT Pretraining Approach
Pointer Networks
MASS-Masked Sequence to Sequence Pre-training for Language Generation
Transformer-XL Attentive Language Models Beyond a Fixed-Length Context
Ubuntu 18.04环境下搭建SSR
Multi-Sample Dropout for Accelerated Training and Better Generalization
标签平滑
深度学习权重初始化
训练神经网络不得不看的33个技巧
Contextual String Embeddings for Sequence Labeling
基于PyTorch实现word2vec模型
Transformer原理和实现
self—attention
认识交叉熵损失
cw2vec Learning Chinese Word Embeddings with Stroke n-gram Information
avatar
lonePatient
一个致力于记录技术的博客
Follow Me
公告
记录和分享一些学习和开源内容,若有任何问题可通过留言板或者微信公众号给我留言,谢谢!