機器學習各研究領域綜述彙總！

點擊下方“AI算法與圖像處理”，一起進步！

重磅乾貨，第一時間送達

作者 | kaiyuan 

整理 | NewBeeNLP

繼續來給大家分享github上的好東西，一個『機器學習領域綜述大列表』，涵蓋了自然語言處理、推薦系統、計算機視覺、深度學習、強化學習等主題。

另外發現源repo中NLP相關的綜述不是很多，於是把一些覺得還不錯的文章添加進去了，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

『收藏等於看完』系列，來看看都有哪些吧， enjoy！

自然語言處理

• 深度學習：Recent Trends in Deep Learning Based Natural Language Processing ^[2]
• 文本分類：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]
• 遷移學習：Exploring Transfer Learning with T5: the Text-To-Text Transfer Transformer ^[6] (Paper ^[7])
• 遷移學習：Neural Transfer Learning for Natural Language Processing ^[8]
• 知識圖譜：A Survey on Knowledge Graphs: Representation, Acquisition and Applications ^[9]
• 命名實體識別：A Survey on Deep Learning for Named Entity Recognition ^[10]
• 關係抽取：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]
• 閱讀理解：Neural Reading Comprehension And Beyond ^[15]
• 閱讀理解：Neural Machine Reading Comprehension: Methods and Trends ^[16]
• 機器翻譯：Neural Machine Translation: A Review ^[17]
• 機器翻譯：A Survey of Domain Adaptation for Neural Machine Translation ^[18]
• 預訓練模型：Pre-trained Models for Natural Language Processing: A Survey ^[19]
• 注意力機制：An Attentive Survey of Attention Models ^[20]
• 注意力機制：An Introductory Survey on Attention Mechanisms in NLP Problems ^[21]
• 注意力機制：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]

推薦系統

• 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]

深度學習

• A State-of-the-Art Survey on Deep Learning Theory and Architectures ^[32]
• 知識蒸餾：Knowledge Distillation: A Survey ^[33]
• 模型壓縮：Compression of Deep Learning Models for Text: A Survey ^[34]
• 遷移學習：A Survey on Deep Transfer Learning ^[35]
• 神經架構搜索：A Comprehensive Survey of Neural Architecture Search-- Challenges and Solutions ^[36]
• 神經架構搜索：Neural Architecture Search: A Survey ^[37]

計算機視覺

• 目標檢測：Object Detection in 20 Years ^[38]
• 對抗性攻擊：Threat of Adversarial Attacks on Deep Learning in Computer Vision ^[39]
• 自動駕駛：Computer Vision for Autonomous Vehicles: Problems, Datasets and State of the Art ^[40]

強化學習

• 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

• 圖：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]

本文參考資料

[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/article/view/11173/26378

[5]

Neural Language Generation: Formulation, Methods, and Evaluation: https://arxiv.org/pdf/2007.15780.pdf

[6]

Exploring Transfer Learning with T5: the Text-To-Text Transfer Transformer: https://ai.googleblog.com/2020/02/exploring-transfer-learning-with-t5.html

[7]

Paper: https://arxiv.org/abs/1910.10683

[8]

Neural Transfer Learning for Natural Language Processing: https://aran.library.nuigalway.ie/handle/10379/15463

[9]

A Survey on Knowledge Graphs: Representation, Acquisition and Applications: https://arxiv.org/abs/2002.00388

[10]

A Survey on Deep Learning for Named Entity Recognition: https://arxiv.org/abs/1812.09449

[11]

More Data, More Relations, More Context and More Openness: A Review and Outlook for Relation Extraction: https://arxiv.org/abs/2004.03186

[12]

Deep Learning for Sentiment Analysis : A Survey: https://arxiv.org/abs/1801.07883

[13]

Deep Learning for Aspect-Level Sentiment Classification: Survey, Vision, and Challenges: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8726353

[14]

Neural Network Models for Paraphrase Identification, Semantic Textual Similarity, Natural Language Inference, and Question Answering: https://www.aclweb.org/anthology/C18-1328/

[15]

Neural Reading Comprehension And Beyond: https://stacks.stanford.edu/file/druid:gd576xb1833/thesis-augmented.pdf

[16]

Neural Machine Reading Comprehension: Methods and Trends: https://arxiv.org/abs/1907.01118

[17]

Neural Machine Translation: A Review: https://arxiv.org/abs/1912.02047

[18]

A Survey of Domain Adaptation for Neural Machine Translation: https://www.aclweb.org/anthology/C18-1111.pdf

[19]

Pre-trained Models for Natural Language Processing: A Survey: https://arxiv.org/abs/2003.08271

[20]

An Attentive Survey of Attention Models: https://arxiv.org/pdf/1904.02874.pdf

[21]

An Introductory Survey on Attention Mechanisms in NLP Problems: https://arxiv.org/abs/1811.05544

[22]

Attention in Natural Language Processing: https://arxiv.org/abs/1902.02181

[23]

A Primer in BERTology: What we know about how BERT works: https://arxiv.org/pdf/2002.12327.pdf

[24]

Beyond Accuracy: Behavioral Testing of NLP Models with CheckList: https://arxiv.org/pdf/2005.04118.pdf

[25]

Evaluation of Text Generation: A Survey: https://arxiv.org/pdf/2006.14799.pdf

[26]

Recommender systems survey: http://irntez.ir/wp-content/uploads/2016/12/sciencedirec.pdf

[27]

Deep Learning based Recommender System: A Survey and New Perspectives: https://arxiv.org/pdf/1707.07435.pdf

[28]

Are We Really Making Progress? A Worrying Analysis of Neural Recommendation Approaches: https://arxiv.org/pdf/1907.06902.pdf

[29]

A Survey of Serendipity in Recommender Systems: https://www.researchgate.net/publication/306075233_A_Survey_of_Serendipity_in_Recommender_Systems

[30]

Diversity in Recommender Systems – A survey: https://papers-gamma.link/static/memory/pdfs/153-Kunaver_Diversity_in_Recommender_Systems_2017.pdf

[31]

A Survey of Explanations in Recommender Systems: http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.418.9237&rep=rep1&type=pdf

[32]

A State-of-the-Art Survey on Deep Learning Theory and Architectures: https://www.mdpi.com/2079-9292/8/3/292/htm

[33]

Knowledge Distillation: A Survey: https://arxiv.org/pdf/2006.05525.pdf

[34]

Compression of Deep Learning Models for Text: A Survey: https://arxiv.org/pdf/2008.05221.pdf

[35]

A Survey on Deep Transfer Learning: https://arxiv.org/pdf/1808.01974.pdf

[36]

A Comprehensive Survey of Neural Architecture Search-- Challenges and Solutions: https://arxiv.org/abs/2006.02903

[37]

Neural Architecture Search: A Survey: https://arxiv.org/abs/1808.05377

[38]

Object Detection in 20 Years: https://arxiv.org/pdf/1905.05055.pdf

[39]

Threat of Adversarial Attacks on Deep Learning in Computer Vision: https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8294186

[40]

Computer Vision for Autonomous Vehicles: Problems, Datasets and State of the Art: https://arxiv.org/pdf/1704.05519.pdf

[41]

A Brief Survey of Deep Reinforcement Learning: https://arxiv.org/pdf/1708.05866.pdf

[42]

Transfer Learning for Reinforcement Learning Domains: http://www.jmlr.org/papers/volume10/taylor09a/taylor09a.pdf

[43]

Review of Deep Reinforcement Learning Methods and Applications in Economics: https://arxiv.org/pdf/2004.01509.pdf

[44]

A Comprehensive Survey of Graph Embedding: Problems, Techniques and Applications: https://arxiv.org/pdf/1709.07604

[45]

From Word to Sense Embeddings:A Survey on Vector Representations of Meaning: https://www.jair.org/index.php/jair/article/view/11259/26454

[46]

Diachronic Word Embeddings and Semantic Shifts: https://arxiv.org/pdf/1806.03537.pdf

[47]

Word Embeddings: A Survey: https://arxiv.org/abs/1901.09069

[48]

A Survey on Contextual Embeddings: https://arxiv.org/abs/2003.07278

[49]

A Survey on Knowledge Graphs: Representation, Acquisition and Applications: https://arxiv.org/abs/2002.00388

[50]

Meta-learning for Few-shot Natural Language Processing: A Survey: https://arxiv.org/abs/2007.09604

[51]

Learning from Few Samples: A Survey: https://arxiv.org/abs/2007.15484

[52]

Meta-Learning in Neural Networks: A Survey: https://arxiv.org/abs/2004.05439

[53]

A Comprehensive Overview and Survey of Recent Advances in Meta-Learning: https://arxiv.org/abs/2004.11149

[54]

Baby steps towards few-shot learning with multiple semantics: https://arxiv.org/abs/1906.01905

[55]

Meta-Learning: A Survey: https://arxiv.org/abs/1810.03548

[56]

A Perspective View And Survey Of Meta-learning: https://www.researchgate.net/publication/2375370_A_Perspective_View_And_Survey_Of_Meta-Learning

[57]

A Survey on Transfer Learning: http://202.120.39.19:40222/wp-content/uploads/2018/03/A-Survey-on-Transfer-Learning.pdf

努力分享優質的計算機視覺相關內容，歡迎關注：

     
        
        
        

      
         
         
         個人微信（如果沒有備註不拉羣！）
     
        
        
        
     
        
        
        

      
         
         
         請註明：
      
         
         
         地區+學校/企業+研究方向+暱稱
     
        
        
        
     
        
        
        

      
         
         
         

     
        
        
        


下載1：何愷明頂會分享

在「AI算法與圖像處理」公衆號後臺回覆：何愷明，即可下載。總共有6份PDF，涉及 ResNet、Mask RCNN等經典工作的總結分析

下載2：終身受益的編程指南：Google編程風格指南

在「AI算法與圖像處理」公衆號後臺回覆：c++，即可下載。歷經十年考驗，最權威的編程規範！


   
      
      
      

    
       
       
       

   
      
      
      
   
      
      
      

    
       
       
       下載3 CVPR2021
   
      
      
      
   
      
      
      

    
       
       
       

   
      
      
      
   
      
      
      

    
       
       
       在「AI算法與圖像處理」公衆號後臺回覆：
    
       
       
       CVPR
    
       
       
       ，即可下載1467篇CVPR 2020論文 和 CVPR 2021 最新論文
   
      
      
      
  
     
     
     

   
      
      
      

    
       
       
       

     
        
        
        

      
         
         
         

       
          
          
          
 
           
 
            
點亮 ，告訴大家你也在看
 
           
 
          
      
         
         
         
     
        
        
        
    
       
       
       
   
      
      
      
  
     
     
     

本文分享自微信公衆號 - AI算法與圖像處理（AI_study）。
如有侵權，請聯繫 [email protected] 刪除。
本文參與“OSC源創計劃”，歡迎正在閱讀的你也加入，一起分享。