baseline:
1、word2vector:Efficient Estimation of Word Representations in Vector Space(基于向量空间中词表示的有效估计)
2、glove:GloVe: Global Vectors for Word Representation(基于全局信息的单词向量表示)EMNLP2014
3、char_embedding(c2w):Finding Function in Form: Compositional Character Models for Open Vocabulary Word Representation（从字符中生成嵌入：用于开放词表示的组合字符模型）EMNLP2015
4、textcnn:Convolutional Neural Networks for Sentence Classification(基于卷积神经网络的句子分类) 会议：E M N L P 2 0 1 4
5、chartextcnn:Character-level Convolutional Networks for Text Classification(使用字符级别的卷积神经网络来做文本分类任务)会议NIPS 2015
6、fasttext:Bag of Tricks for Efficient Text Classification:Fasttext: 对于高效率文本分类的一揽子技巧 会议：E A C L 2 0 1 7
7、deep_nmt:Sequence to Sequence Learning with Neural Networks(使用神经网络来做序列到序列的学习)会议：N I P S 2014
8、attention_nmt:Neural Machine Translation by Jointly Learning to Align and Translate(联合学习对齐和翻译的神经机器翻译模型）会议 :ICLR2015
9、han_attention:Hierarchical Attention Networks for Document Classification(使用层次注意力网络做文档分类）会议：NAAC2016
10、sgn:SGM Sequence Generation Model for Multi-Label Classification(使用序列生成模型做多标签文本分类）会议：coling2018 best paper
机器翻译
loung_nmt:Effective Approaches to Attention-based Neural Machine Translation(基于注意力机制的有效神经机器翻译方法)E M N L P 2015
coverage:Modeling Coverage for Neural Machine Translation(神经机器翻译的翻译覆盖方法）ACL2016
subword_nmt:Neural Machine Translation of Rare Words with Subword Units使用子词来解决神经机器翻译的罕见词问题 ACL2016
情感分析：
TextRNN：Recurrent Neural Network for Text Classification with Multi Task Learning 循环神经网络用于多任务学习的文本分类（IJCAI2016）
TreeLSTM:Improved Semantic Representations From Tree-Structured Long Short- Term Memory Networks从树结构的长短期记忆网络改进语义表示 ACL2015
TD-LSTM_TC-LSTM_AT-LSTM：Attention-based LSTM for Aspect-level Sentiment Classification基于注意的LSTM用于Aspect-level的情感分类EMNLP2016
Effective LSTMs for Target-Dependent Sentiment Classification：有效的LSTM用于Target-Dependent的情感分类 COLING2016
MemNet:Aspect Level Sentiment classification with Deep Memory Network基于深度记忆网络在Aspect-level的情感分类 EMNLP2016
End-To-End Memory Networks
Interactive Attention Networks for Aspect-Level Sentiment Classification
MEMORY NETWORKS
NEURAL MACHINE TRANSLATION BY JOINTLY LEARNING TO ALIGN AND TRANSLATE
BERT-ABSA:BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding语言理解的深度双向Transformers的预训练 NAACL2019 bestpaper
Attention Is All You Need
NLP-预训练模型
transformer：Attention is all you need注意力机制是大家需要掌握的 NIPS
transformer_xl:Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context 超出固定长度上下文的注意力语言模型 ACL
elmo:Deep contextualized word representations 基于深度上下文的词表征 NAACL
gpt: Improving Language Understanding by Generative Pre-Training 通过生成式预训练提升语义理解
bert:BERT:Pre-training of Deep Bidirectional Transformers for Language Understanding 预训练的深度双向Transformers用于语义理解
ulmfit:Universal Language Model Fine-tuning for Text Classification 微调通用的语言模型用于文本分类任务 2017EMNLp
ALBERT:ALBERT: A LITE BERT FOR SELF-SUPERVISED LEARNING OF LANGUAGE REPRESENTATIONS精简版的bert用于语言表征的自监督学习
mass:Masked Sequence to Sequence Pre-training for Language Generation 屏蔽序列到序列的预训练用于语言生成 2019PMLR
xlnet:Generalized Autoregressive Pretraining for Language Understanding 通用化的自回归预训练模型用于语言理解 2019NeurlPS
electra:PRE-TRAINING TEXT ENCODERS AS DISCRIMINATORS RATHER THAN GENERATORS 预训练的文本编码器作为判别器而不是生成器 2020ICLR
NLP阅读理解:
MRC:Teaching Machines to Read and Comprehend 指导机器阅读与理解 2015NIPS
BIDAF：Bidirectional Attention Flow for Machine Comprehension 应用于机器阅读理解的双向注意力机制 2017ICLR
PGNet:Get To The Point :Summarization with Pointer-Generator Networks指针生成网络在文本摘要的应用 2017ACL
adv:Improving the Robustness of Question Answering Systems to Question Paraphrasing 改善阅读理解系统中的鲁棒性问题 2019ACL
xlnet:Generalized Autoregressive Pretraining for Language Understanding 对于语言理解的生成式自回归预训练模型 2019Nips
强化学习：
DQN：Playing Atari with Deep Reinforcement Learning 使用深度强化学习玩Atari游戏 NIPS 2013
DQN改进:Deep Reinforcement Learning with Double Q-Learning带有Double-Q Learning 的深度强化学习 AAAI2016
Priortized Experience Replay 优先化经验回放 ICLR2016
Dueling Network Atchitectures for Deep Reinforcement Learning使用Duel网络结构的深度强化学习 arxiv2016
C51: A Distributional Perspective on Reinforcement Learning 基于分布式视角的强化学习 ICML2017
QRDQN：Distributional Reinforcement Learning with Quantile Regression 分位数回归的分布式强化学习 AAAI2018
REINFORCE:Policy Gradient Methods for Reinforcement Learning with Function Approximation 强化学习的策略梯度方法与函数估计 2000NIPS
PPO：Proximal Policy Optimization Algorithms 近似策略优化算法 arxiv2017
DDPG:Continuous Control with Deep Reinforcement Learning 使用深度强化学习的连续控制 ICLR2016
TD3:Addressing Function Approximation Error in Actor-Critic Methods Actor-Critic方法中的函数估计误差 2018ICML
SQL:Reinforcement Learning with Deep Energy-Based Policies 使用深度能量策略网络的强化学习 ICML2017
SAC:Soft Actor-Critic : Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor ICML2018
图神经网络
Node2vec:node2vec:Scalable Feature Learning for Networks大规模网络节点的表征学习 kdd2016
LINE:LINE:Large-scale Information Network Embedding 大规模信息网络特征表示 WWW2015
SDNE:Structural Deep Network Embedding 结构化深度网络表示 KDD2016
metapath2vec:metapath2vec:Scalable Representation Learning for Heterogenerous Networks 结构化深度网络表示 KDD2017
TransE:Translating Embeddings for Modeling Multi-relational Data 知识图谱向量化表示 NIPS2013
GAT：Graph Attention Networks 图注意力网络 ICLR2018
GraphSAGE:Inductive Representation Learning on Large Graphs 大规模网络的归纳式学习 NIPS2018
GCN:Semi-Supervised Classification with Graph Convolutional Networks图卷积神经网络的半监督分类 ICLR2017
GGNN:Gated Graph Sequence Neural Networks 门控序列图神经网络 ICLR2016
MPNN：Neural Message Passing for Quantum Chemistry 神经网络消息传递应用量子化学 ICML2017
文本匹配：
DSSM：Learning Deep Structured Semantic Models for Web Search using Clickthrough Data 利用点击数据学习网页搜索中深层结构化语义模型 CIKM2013
SiameseNet:Learning Text Similarity with Siamese Recurrent Networks 利用孪生循环神经网络学习文本相似性 ACL2016
Comp-Agg:A COMPARE-AGGREGATE MODEL FOR MATCHING TEXT SEQUENCES 文本序列处理中的比较-聚合模型 ICLR2017
ESIM:Enhanced LSTM for Natural Language Inference ACL2017
BiMPM:Bilateral Multi-Perspective Matching for Natural Language Sentences 自然语言文本中的双向多视角匹配 IJCAI2017
关系抽取:
cnn:Relation Classification via Convolutional Deep Neural Network 基于深度卷积神经网络的关系识别 COLING2014
crcnn与pcnn:Classifying Relations by Ranking with Convolutional Neural Networks基于卷积神经网络排序进行关系识别 ACL|IJCNLP2015
Distant Supervision for Relation Extraction via Piecewise Convolutional Neural Networks pcnn实现远程监督在关系提取中的应用EMNLP2015
atr-blsrm:Attention-Based Bidirectional Long Short-Term Memory Networks for Relation Classification 基于双向LSTM及注意力机制的关系分类 ACL2016
LSTM-LSTM-bias:Joint Extraction of Entities and Relations Based on a Novel Tagging Scheme基于一种新的标注策略进行实体和关系的联合抽取ACL2017
CasRel:A Novel Cascade Binary Tagging Framework for Relational Triple Extraction 关系三元组抽取-- 一种新的级联二元标注框架 ACL2020
命名实体识别：
Bidirectional LSTM-CRF Models for Sequence Tagging 用于序列标注的双向LSTM-CRF模型
Chinese NER Using Lattice LSTM 基于网格LSTM的中文命名实体识别 ACL2018
CNN-Based Chinese NER with Lexicon Rethinking 基于LR-CNN的中文命名实体识别IJCAI 2019
A Lexicon-Based Graph Neural Network for Chinese NER基于词典的图神经网络解决命名实体识别 EMNLP2019
TENER:Adapting Transformer Encoder for Named Entity Recognition 适用于命名实体识别的改进Transformer ACL2019
Simplify the Usage of Lexicon in Chinese NER 简化中文NER中词典的使用 ACL2020