作者：kaiyuan，来源：NewBeeNLP

继续来给大家分享github上的干货，一个『机器学习领域综述大列表』，涵盖了自然语言处理、推荐系统、计算机视觉、深度学习、强化学习等主题。

另外发现源repo中NLP相关的综述不是很多，于是把一些觉得还不错的文章添加进去了，重新整理更新在 AI-Surveys^[1] 中。

• ml-surveys: https://github.com/eugeneyan/ml-surveys

• AI-Surveys: https://github.com/KaiyuanGao/AI-Surveys

『收藏等于看完』系列，来看看都有哪些吧， enjoy！

自然语言处理

• 深度学习：Recent Trends in Deep Learning Based Natural Language Processing^[2]

• 文本分类：Deep Learning Based Text Classification: A Comprehensive Review^[3]

• 文本生成：Survey of the SOTA in Natural Language Generation: Core tasks, applications and evaluation^[4]

• 文本生成：Neural Language Generation: Formulation, Methods, and Evaluation^[5]

• 迁移学习：Exploring Transfer Learning with T5: the Text-To-Text Transfer Transformer^[6] (Paper^[7])

• 迁移学习：Neural Transfer Learning for Natural Language Processing^[8]

• 知识图谱：A Survey on Knowledge Graphs: Representation, Acquisition and Applications^[9]

• 命名实体识别：A Survey on Deep Learning for Named Entity Recognition^[10]

• 关系抽取：More Data, More Relations, More Context and More Openness: A Review and Outlook for Relation Extraction^[11]

• 情感分析：Deep Learning for Sentiment Analysis : A Survey^[12]

• ABSA情感分析：Deep Learning for Aspect-Level Sentiment Classification: Survey, Vision, and Challenges^[13]

• 文本匹配：Neural Network Models for Paraphrase Identification, Semantic Textual Similarity, Natural Language Inference, and Question Answering^[14]

• 阅读理解：Neural Reading Comprehension And Beyond^[15]

• 阅读理解：Neural Machine Reading Comprehension: Methods and Trends^[16]

• 机器翻译：Neural Machine Translation: A Review^[17]

• 机器翻译：A Survey of Domain Adaptation for Neural Machine Translation^[18]

• 预训练模型：Pre-trained Models for Natural Language Processing: A Survey^[19]

• 注意力机制：An Attentive Survey of Attention Models^[20]

• 注意力机制：An Introductory Survey on Attention Mechanisms in NLP Problems^[21]

• 注意力机制：Attention in Natural Language Processing^[22]

• BERT：A Primer in BERTology: What we know about how BERT works^[23]

• Beyond Accuracy: Behavioral Testing of NLP Models with CheckList^[24]

• Evaluation of Text Generation: A Survey^[25]

推荐系统

• Recommender systems survey^[26]

• Deep Learning based Recommender System: A Survey and New Perspectives^[27]

• Are We Really Making Progress? A Worrying Analysis of Neural Recommendation Approaches^[28]

• A Survey of Serendipity in Recommender Systems^[29]

• Diversity in Recommender Systems – A survey^[30]

• A Survey of Explanations in Recommender Systems^[31]

深度学习

• A State-of-the-Art Survey on Deep Learning Theory and Architectures^[32]

• 知识蒸馏：Knowledge Distillation: A Survey^[33]

• 模型压缩：Compression of Deep Learning Models for Text: A Survey^[34]

• 迁移学习：A Survey on Deep Transfer Learning^[35]

• 神经架构搜索：A Comprehensive Survey of Neural Architecture Search-- Challenges and Solutions^[36]

• 神经架构搜索：Neural Architecture Search: A Survey^[37]

计算机视觉

• 目标检测：Object Detection in 20 Years^[38]

• 对抗性攻击：Threat of Adversarial Attacks on Deep Learning in Computer Vision^[39]

• 自动驾驶：Computer Vision for Autonomous Vehicles: Problems, Datasets and State of the Art^[40]

强化学习

• A Brief Survey of Deep Reinforcement Learning^[41]

• Transfer Learning for Reinforcement Learning Domains^[42]

• Review of Deep Reinforcement Learning Methods and Applications in Economics^[43]

Embeddings

• 图：A Comprehensive Survey of Graph Embedding: Problems, Techniques and Applications^[44]

• 文本：From Word to Sense Embeddings:A Survey on Vector Representations of Meaning^[45]

• 文本：Diachronic Word Embeddings and Semantic Shifts^[46]

• 文本：Word Embeddings: A Survey^[47]

• A Survey on Contextual Embeddings^[48]

Meta-learning & Few-shot Learning

• A Survey on Knowledge Graphs: Representation, Acquisition and Applications^[49]

• Meta-learning for Few-shot Natural Language Processing: A Survey^[50]

• Learning from Few Samples: A Survey^[51]

• Meta-Learning in Neural Networks: A Survey^[52]

• A Comprehensive Overview and Survey of Recent Advances in Meta-Learning^[53]

• Baby steps towards few-shot learning with multiple semantics^[54]

• Meta-Learning: A Survey^[55]

• A Perspective View And Survey Of Meta-learning^[56]

其他

• A Survey on Transfer Learning^[57]

本文参考资料

[1]

AI-Surveys: https://github.com/KaiyuanGao/AI-Surveys

[2]

Recent Trends in Deep Learning Based Natural Language Processing: https://arxiv.org/pdf/1708.02709.pdf

[3]

Deep Learning Based Text Classification: A Comprehensive Review: https://arxiv.org/pdf/2004.03705

[4]

Survey of the SOTA in Natural Language Generation: Core tasks, applications and evaluation: https://www.jair.org/index.php/jair