Neural network methods for natural language processing

著者

• Goldberg, Yoav

書誌事項

Neural network methods for natural language processing

Yoav Goldberg

（Synthesis lectures on human language technologies, 37）

Morgan & Claypool, c2017

注記

Includes bibliographical references (p. 253-285)

内容説明・目次

内容説明

Neural networks are a family of powerful machine learning models and this book focuses on their application to natural language data. The first half of the book (Parts I and II) covers the basics of supervised machine learning and feed-forward neural networks, the basics of working with machine learning over language data, and the use of vector-based rather than symbolic representations for words. It also covers the computation-graph abstraction, which allows to easily define and train arbitrary neural networks, and is the basis behind the design of contemporary neural network software libraries. The second part of the book (Parts III and IV) introduces more specialized neural network architectures, including 1D convolutional neural networks, recurrent neural networks, conditioned-generation models, and attention-based models. These architectures and techniques are the driving force behind state-of-the-art algorithms for machine translation, syntactic parsing, and many other applications. Finally, we also discuss tree-shaped networks, structured prediction, and the prospects of multi-task learning.

目次

Preface Acknowledgments Introduction Learning Basics and Linear Models Learning Basics and Linear Models From Linear Models to Multi-layer Perceptrons Feed-forward Neural Networks Neural Network Training Features for Textual Data Case Studies of NLP Features From Textual Features to Inputs Language Modeling Pre-trained Word Representations Pre-trained Word Representations Using Word Embeddings Case Study: A Feed-forward Architecture for Sentence Case Study: A Feed-forward Architecture for Sentence Meaning Inference Ngram Detectors: Convolutional Neural Networks Recurrent Neural Networks: Modeling Sequences and Stacks Concrete Recurrent Neural Network Architectures Modeling with Recurrent Networks Modeling with Recurrent Networks Conditioned Generation Modeling Trees with Recursive Neural Networks Modeling Trees with Recursive Neural Networks Structured Output Prediction Cascaded, Multi-task and Semi-supervised Learning Conclusion Bibliography Author's Biography

「Nielsen BookData」 より

詳細情報

• NII書誌ID(NCID): BB23652861
• ISBN:
  • 9781627052986
• 出版国コード: us
• タイトル言語コード: eng
• 本文言語コード: eng
• 出版地: [San Rafael, Calif]
• ページ数/冊数: xxii, 287 p.
• 大きさ: 24 cm
• 親書誌ID:
  • BA89506182