 Название: Neural Representations of Natural Language
Автор: Lyndon White, Roberto Togneri
Издательство: Springer
Год: 2018 (2019 Edition)
Страниц: 132
Язык: английский
Формат: pdf (true), epub
Размер: 10.17 MB
This book offers an introduction to modern natural language processing using machine learning, focusing on how neural networks create a machine interpretable representation of the meaning of natural language. Language is crucially linked to ideas – as Webster’s 1923 “English Composition and Literature” puts it: “A sentence is a group of words expressing a complete thought”. Thus the representation of sentences and the words that make them up is vital in advancing artificial intelligence and other “smart” systems currently being developed. Providing an overview of the research in the area, from Bengio et al.’s seminal work on a “Neural Probabilistic Language Model” in 2003, to the latest techniques, this book enables readers to gain an understanding of how the techniques are related and what is best for their purposes.
As well as a introduction to neural networks in general and recurrent neural networks in particular, this book details the methods used for representing words, senses of words, and larger structures such as sentences or documents. The book highlights practical implementations and discusses many aspects that are often overlooked or misunderstood. The book includes thorough instruction on challenging areas such as hierarchical softmax and negative sampling, to ensure the reader fully and easily understands the details of how the algorithms function. Combining practical aspects with a more traditional review of the literature, it is directly applicable to a broad readership. It is an invaluable introduction for early graduate students working in natural language processing; a trustworthy guide for industry developers wishing to make use of recent innovations; and a sturdy bridge for researchers already familiar with linguistics or machine learning wishing to understand the other.
Contents:
1 Introduction to Neural Networks for Machine Learning 1
1. 1 Neural Networks 2
1. 2 Function Approximation 4
1. 3 Network Hyper-Parameters 4
1. 4 Training 10
1. 5 Some Examples of Common Neural Network Architectures 14
2 Recurrent Neural Networks for Sequential Processing 23
2. 1 Recurrent Neural Networks 24
2. 2 General RNN Structures 25
2. 3 Inside the Recurrent Unit 28
2. 4 Further Variants 34
3 Word Representations 37
3. 1 Representations for Language Modeling 39
3. 1. 1 The Neural Probabilistic Language Model 41
3. 1. 2 RNN Language Models 47
3. 2 Acausal Language Modeling 48
3. 3 Co-location Factorisation 53
3. 4 Hierarchical Softmax and Negative Sampling 56
3. 5 Natural Language Applications – Beyond Language Modeling 66
3. 6 Aligning Vector Spaces Across Languages 67
4 Word Sense Representations 73
5 Sentence Representations and Beyond 93
References 119
Index 121
Скачать Neural Representations of Natural Language
|
Навигация
Вход на сайт
Реклама
Neural Representations of Natural Language 
