【Github】nlp-journey: NLP相关代码、书目、论文、博文、算法、项目资源链接

推荐Github上一个NLP相关的项目：msgi/nlp-journey

项目地址，阅读原文可以直达，欢迎参与和Star：

https://github.com/msgi/nlp-journey

这个项目的作者是AINLP交流群里的慢时光同学，该项目收集了NLP相关的一些代码, 包括词向量(Word Embedding)、命名实体识别(NER)、文本分类(Text Classificatin)、文本生成、文本相似性(Text Similarity)计算等，基于keras和tensorflow，也收集了相关的书目、论文、博文、算法、项目资源链接，并且很细致的做了分类。

以下来自该项目介绍页，点击阅读原文可以直达相关资源链接。

---

基础

• 基础知识

• 常见问题

• 实践笔记

经典书目(百度云 提取码：b5qq)

• Deep Learning.深度学习必读. 原书地址

• 斯坦福大学《语音与语言处理》第三版：NLP必读. 原书地址

• Neural Networks and Deep Learning. 入门必读. 原书地址

• 复旦大学《神经网络与深度学习》邱锡鹏教授. 原书地址

• CS224d: Deep Learning for Natural Language Processing. 课件地址

必读论文

• EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks.地址

• A Neural Probabilistic Language Model. 地址

• Transformer. 地址

• Transformer-XL. 地址

• Convolutional Neural Networks for Sentence Classification. 地址

• Attention-Based Bidirectional Long Short-Term Memory Networks for Relation Classification. 地址

• A Question-Focused Multi-Factor Attention Network for Question Answering. 地址

• AutoCross: Automatic Feature Crossing for Tabular Data in Real-World Applications. 地址

• GloVe: Global Vectors for Word Representation. 官网

• A Deep Ensemble Model with Slot Alignment for Sequence-to-Sequence Natural Language Generation. 地址

• The Design and Implementation of XiaoIce, an Empathetic Social Chatbot. 地址

• A Knowledge-Grounded Neural Conversation Model. 地址

• Neural Generative Question Answering. 地址

• A Sensitivity Analysis of (and Practitioners’ Guide to) Convolutional Neural Networks for Sentence Classification. 地址

• ImageNet Classification with Deep Convolutional Neural Networks. 地址

• Network In Network. 地址,翻译

• Long Short-term Memory. 地址

• Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation. 地址

• Get To The Point: Summarization with Pointer-Generator Networks. 地址

• Generative Adversarial Text to Image Synthesis. 地址

• Image-to-Image Translation with Conditional Adversarial Networks. 地址

• Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network. 地址

• Unsupervised Learning of Visual Structure using Predictive Generative Networks. 地址

• Learning to Rank Short Text Pairs with Convolutional Deep Neural Networks. 地址

• Event Extraction via Dynamic Multi-Pooling Convolutional Neural. 地址

• Low-Memory Neural Network Training:A Technical Report. 地址

• Language Models are Unsupervised Multitask Learners. 地址

• Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context. 地址

• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. 地址

• SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient. 地址

必读博文

• The Illustrated Transformer.博文

• Attention-based-model. 地址

• KL divergence. 地址

• Building Autoencoders in Keras. 地址

• Modern Deep Learning Techniques Applied to Natural Language Processing. 地址

• Node2vec embeddings for graph data. 地址

• Bert解读. 地址 地址

• 难以置信！LSTM和GRU的解析从未如此清晰（动图+视频）。地址

已实现算法

• 构建词向量

•  fasttext(skipgram+cbow)

•  gensim(word2vec)

• 数据增强

•  eda

• 分类算法

•  svm

•  fasttext

•  textcnn

•  bilstm+attention

•  rcnn

•  han

• NER

•  bilstm+crf

• 文本相似度

•  siamese

相关github项目

• keras-gpt-2. 地址

• textClassifier. 地址

• attention-is-all-you-need-keras. 地址

• BERT_with_keras. 地址

• SeqGAN. 地址

相关博客

• 莫坠青云志

• 彗双智能-Keras源码分析

• 机器之心

• colah

• ZHPMATRIX

• wildml

• 徐阿衡

• 零基础入门深度学习

相关会议

• Association of Computational Linguistics(计算语言学协会). ACL

• Empirical Methods in Natural Language Processing. EMNLP

• International Conference on Computational Linguistics. COLING

• Neural Information Processing Systems(神经信息处理系统会议). NIPS

• AAAI Conference on Artificial Intelligence. AAAI

• International Joint Conferences on AI. IJCAI

• International Conference on Machine Learning(国际机器学习大会). ICML