本资源整理了自然语言处理常见任务相关的文档、论文和代码，包括主题模型、word embedding、命名实体识别、文本分类、文本生成、文本相似性、机器翻译等领域。所有代码都在intensorflow 2.0中实现。
资源整理自网络，源文链接：https://github.com/msgi/nlp-journey
1. 基础知识
•basics
•tutorials
•notes
•frequent questions
2. 免费书籍
1.Handbook of Graphical Models. online
2.Deep Learning. online
3.Neural Networks and Deep Learning. online
4.Speech and Language Processing. online
3. 经典论文
01) NLP相关
1.BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.
2.GPT-2: Language Models are Unsupervised Multitask Learners.
3.Transformer-XL: Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context.
4.XLNet: Generalized Autoregressive Pretraining for Language Understanding.
5.RoBERTa: Robustly Optimized BERT Pretraining Approach.
6.DistilBERT: a distilled version of BERT: smaller, faster, cheaper and lighter.
7.ALBERT: A Lite BERT for Self-supervised Learning of Language Representations.
8.T5: Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer.
02) NLP模型相关
1.LSTM(Long Short-term Memory).
2.Sequence to Sequence Learning with Neural Networks.
3.Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation.
4.Residual Network(Deep Residual Learning for Image Recognition).
5.Dropout(Improving neural networks by preventing co-adaptation of feature detectors).
6.Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift.
03) 摘要抽取
1.An overview of gradient descent optimization algorithms.
2.Analysis Methods in Neural Language Processing: A Survey.
3.Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer.
4.A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications.
5.A Gentle Introduction to Deep Learning for Graphs.
6.A Survey on Deep Learning for Named Entity Recognition.
7.More Data, More Relations, More Context and More Openness: A Review and Outlook for Relation Extraction.
8.Deep Learning Based Text Classification: A Comprehensive Review.
9.Pre-trained Models for Natural Language Processing: A Survey.
10.A Survey on Contextual Embeddings.
11.A Survey on Knowledge Graphs: Representation, Acquisition and Applications.
12.Knowledge Graphs.
13.Pre-trained Models for Natural Language Processing: A Survey.
04) 预训练模型
1.A Neural Probabilistic Language Model.
2.word2vec Parameter Learning Explained.
3.Language Models are Unsupervised Multitask Learners.
4.An Empirical Study of Smoothing Techniques for Language Modeling.
5.Efficient Estimation of Word Representations in Vector Space.
6.Distributed Representations of Sentences and Documents.
7.Enriching Word Vectors with Subword Information(FastText).
8.GloVe: Global Vectors for Word Representation. online
9.ELMo (Deep contextualized word representations).
10.Pre-Training with Whole Word Masking for Chinese BERT.
05) 文本分类
1.Bag of Tricks for Efficient Text Classification (FastText).
2.Convolutional Neural Networks for Sentence Classification.
3.Attention-Based Bidirectional Long Short-Term Memory Networks for Relation Classification.
06) 文本生成
1.A Deep Ensemble Model with Slot Alignment for Sequence-to-Sequence Natural Language Generation.
2.SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient.
07) 文本相似性
1.Learning to Rank Short Text Pairs with Convolutional Deep Neural Networks.
2.Learning Text Similarity with Siamese Recurrent Networks.
3.A Deep Architecture for Matching Short Texts.
08) 问答
1.A Question-Focused Multi-Factor Attention Network for Question Answering.
2.The Design and Implementation of XiaoIce, an Empathetic Social Chatbot.
3.A Knowledge-Grounded Neural Conversation Model.
4.Neural Generative Question Answering.
5.Sequential Matching Network A New Architecture for Multi-turn Response Selection in Retrieval-Based Chatbots．
6.Modeling Multi-turn Conversation with Deep Utterance Aggregation．
7.Multi-Turn Response Selection for Chatbots with Deep Attention Matching Network．
8.Deep Reinforcement Learning For Modeling Chit-Chat Dialog With Discrete Attributes.
09) 神经机器翻译
1.Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation.
2.Neural Machine Translation by Jointly Learning to Align and Translate.
3.Transformer (Attention Is All You Need).
10) 摘要生成
1.Get To The Point: Summarization with Pointer-Generator Networks.
2.Deep Recurrent Generative Decoder for Abstractive Text Summarization.
11) 关系抽取
1.Distant Supervision for Relation Extraction via Piecewise Convolutional Neural Networks.
2.Neural Relation Extraction with Multi-lingual Attention.
3.FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation.
4.End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures.
4. 相关文章
•如何学习自然语言处理（综合版）. url
•The Illustrated Transformer.url
•Attention-based-model. url
•Modern Deep Learning Techniques Applied to Natural Language Processing. url
•难以置信！LSTM和GRU的解析从未如此清晰（动图+视频）。url
•从语言模型到Seq2Seq：Transformer如戏，全靠Mask. url
•Applying word2vec to Recommenders and Advertising. url
•2019 NLP大全：论文、博客、教程、工程进展全梳理. url
5. Github地址
•transformers. github
•HanLP. github
6. 经典博客
•52nlp
•科学空间/信息时代
•刘建平Pinard
•零基础入门深度学习
•Jay Alammar
•Andrej Karpathy blog
•Edwin Chen
•Distill
往期精品内容推荐
精品课程推荐 | 备战CV研究生必读指南：研究方向及课题选择、论文产出
中文版-《可解释的机器学习-黑盒模型可解释性理解指南》pdf免费分享
伯克利-《神经技术导论课程2020（带字幕）》课程视频及ppt分享
20年算法校招编程-剑指offer、Leetcode常考题目及解法分享
斯坦福2020年免费新课-CS221人工智能原理与技术-视频、ppt、参考书籍分享
19年11月最新-《TensorFlow 2.0深度学习算法实战教材》-中文版教材+随书代码+视频-分享.pdf
免费开源书-《基于PyTorch的深度学习技术进步》pdf分享