Deep Learning for Natural Language Processing MEAP V07
Copyright
Welcome
Brief contents
Chapter 1: Deep learning for NLP
1.1 Overview of the book
1.2 A selection of machine learning methods for NLP
1.2.1 The perceptron
1.2.2 Support Vector Machines
1.2.3 Memory-based learning
1.3 Deep Learning
1.4 Vector representations of language
1.4.1 Representational vectors
1.4.2 Operational vectors
1.5 Vector sanitization
1.5.1 The Hashing trick
1.5.2 Vector normalization
1.6 Wrapping up
1.7 References
Chapter 2: Deep learning and language: the basics
2.1 Basic architectures of deep learning
2.1.1 Deep multilayer perceptrons
2.1.2 Two basic operators: spatial and temporal
2.2 Deep learning and NLP: a new paradigm
2.3 Wrapping up
Chapter 3: Text embeddings
3.1 Embeddings
3.1.1 Embedding by hand: representational embeddings
3.1.2 Learning to embed: procedural embeddings
3.2 From words to vectors: word2vec
3.3 From documents to vectors: doc2vec
3.4 Wrapping up
3.5 External resources
Chapter 4: Textual similarity
4.1 The problem
4.2 The data
4.2.1 Authorship attribution and verification data
4.3 Data representation
4.3.1 Segmenting documents
4.3.2 Word-level information
4.3.3 Subword-level information
4.4 Models for measuring similarity
4.5 Authorship attribution
4.5.1 Multilayer perceptrons
4.5.2 CNNs for text
4.6 Authorship verification
4.6.1 Siamese networks: network twins
4.7 Wrap up
Chapter 5: Sequential NLP and memory
5.1 Memory and language
5.1.1 The problem: Question Answering
5.2 Data and data processing
5.3 Question Answering with sequential models
5.3.1 RNNs for Question Answering
5.3.2 LSTMs for Question Answering
5.3.3 End-to-end memory networks for Question Answering
5.4 Conclusion
5.5 Further reading
5.6 Data and software resources
Chapter 6: Episodic memory for NLP
6.1 Memory networks for sequential NLP
6.2 Data and data processing
6.2.1 PP attachment data
6.2.2 Dutch diminutive data
6.2.3 Spanish part-of-speech data
6.3 Strongly supervised memory networks: experiments and results
6.3.1 PP-attachment
6.3.2 Dutch diminutives
6.3.3 Spanish part-of-speech tagging
6.4 Semi-supervised memory networks
6.5 Semi-supervised memory networks: experiments and results
6.6 Summary
6.7 Code and data
6.8 Further reading
Chapter 7: Attention
7.1 Neural attention
7.2 Data
7.3 Static attention: MLP
7.4 Temporal attention: LSTM
7.4.1 Experiments
7.5 Summary
7.6 Further reading
Chapter 8: Multitask learning
8.1 Introduction
8.2 Data
8.3 Consumer reviews: Yelp and Amazon
8.3.1 Data handling
8.3.2 Hard parameter sharing
8.3.3 Soft parameter sharing
8.3.4 Mixed parameter sharing
8.4 Reuters topic classification
8.4.1 Data handling
8.4.2 Hard parameter sharing
8.4.3 Soft parameter sharing
8.4.4 Mixed parameter sharing
8.5 Part-of-speech and named entity recognition data
8.5.1 Data handling
8.5.2 Hard parameter sharing
8.5.3 Soft parameter sharing
8.5.4 Mixed parameter sharing
8.6 Conclusions
8.7 Further reading
Appendix: A random walk through NLP
A.1 Deep versus shallow linguistics
Notes