https://www.kspub.co.jp/book/detail/1529243.html
Chapter 1: natural language processing approach 1.1 Traditional Natural Language Processing 1.2 Expectations for [deep learning 1.3 Characteristics of text data 1.4 Expansion into other fields
Chapter 2: Fundamentals of Neural Networks 2.1 Supervised learning 2.2 Forward Propagating Neural Networks 2.3 Activation Functions 2.4 Gradient method 2.5 Error Back Propagation Method 2.6 Recurrent Neural NetworksRNN 2.7 Gated Recurrent Neural Networks
- LSTM
- GRU 2.8 Tree-structured recurrent neural nets
- recursive neural networks = Tree-RNN 2.9 Convolutional Neural NetworksCNN
Chapter 3: Fundamentals of Deep Learning in Linguistic Processing 3.1 Preparation: Bridging the world of symbols and the world of vectors 3.2 Language Model 3.3 distributed representation
Chapter 4: Developments in Deep Learning Specific to Linguistic Processing 4.1 attention mechanism 4.2 Memory Network 4.3 Output Layer Acceleration
Chapter 5 Applications 5.1 Machine Translation 5.2 Document Summary 5.3 Dialogue 5.4 Question and Answer
Chapter 6: Techniques to Improve Generalization Performance 6.1 Decomposition of generalization error 6.2 Methods Effective in Reducing Estimation Error 6.3 Methods Effective in Reducing Optimization Error 6.4 Super-parameter selection
Chapter 7 Implementation 7.1 GPUs and GPGPUs 7.2 Minibatching in RNNs 7.3 Random sampling 7.4 Reducing Memory Usage 7.5 Implementation of Error Back Propagation Method
This page is auto-translated from /nishio/深層学習による自然言語処理 using DeepL. If you looks something interesting but the auto-translated English is not good enough to understand it, feel free to let me know at @nishio_en. I’m very happy to spread my thought to non-Japanese readers.