Tree-Based Convolutional Neural Networks Principles and Applications /

• Main Authors: Mou, Lili (Author, http://id.loc.gov/vocabulary/relators/aut), Jin, Zhi (http://id.loc.gov/vocabulary/relators/aut)
• Corporate Author: SpringerLink (Online service)
• Format: Electronic eBook
• Language: English
• Published: Singapore : Springer Singapore : Imprint: Springer, 2018.
• Edition: 1st ed. 2018.
• Series: SpringerBriefs in Computer Science,
• Subjects: Artificial intelligence.; Data mining.; Computational intelligence.; Software engineering.; Artificial Intelligence.; Data Mining and Knowledge Discovery.; Computational Intelligence.; Software Engineering.

This book proposes a novel neural architecture, tree-based convolutional neural networks (TBCNNs),for processing tree-structured data. TBCNNsare related to existing convolutional neural networks (CNNs) and recursive neural networks (RNNs), but they combine the merits of both: thanks to their short p...

Table of Contents:

• Introduction
• Preliminaries and Related Work
• General Concepts of Tree-Based Convolutional Neural Networks (TBCNNs)
• TBCNN for Programs' Abstract Syntax Trees (ASTs)
• TBCNN for Constituency Trees in Natural Language Processing
• TBCNN for Dependency Trees in Natural Language Processing
• Concluding Remarks.