Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Tree-Based Convolutional Neural NetworksTBCNN for Dependency Trees in Natural Language Processing

Tree-Based Convolutional Neural Networks: TBCNN for Dependency Trees in Natural Language Processing [This chapter applies tree-based convolution to the dependency parse trees of natural language sentences, resulting in a new variant d-TBCNN. Since dependency trees are different from abstract syntax trees in Chap. 4 and constituency trees in Chap. 5, we need to design new model gadgets for d-TBCNN. The model is evaluated on two sentence classification tasks (sentiment analysis and question classification) and a sentence matching task. In the sentence classification tasks, d-TBCNN outperforms previous state-of-the-art results, whereas in the sentence matching task, d-TBCNN achieves comparable performance to the previous state-of-the-art model, which has a higher matching complexity.] http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png

Tree-Based Convolutional Neural NetworksTBCNN for Dependency Trees in Natural Language Processing

Download PDF
16 pages

Loading next page...
 
/lp/springer-journals/tree-based-convolutional-neural-networks-tbcnn-for-dependency-trees-in-qz899gotCp

References (23)

Publisher
Springer Singapore
Copyright
© The Author(s) 2018
ISBN
978-981-13-1869-6
Pages
73 –89
DOI
10.1007/978-981-13-1870-2_6
Publisher site
See Chapter on Publisher Site

Abstract

[This chapter applies tree-based convolution to the dependency parse trees of natural language sentences, resulting in a new variant d-TBCNN. Since dependency trees are different from abstract syntax trees in Chap. 4 and constituency trees in Chap. 5, we need to design new model gadgets for d-TBCNN. The model is evaluated on two sentence classification tasks (sentiment analysis and question classification) and a sentence matching task. In the sentence classification tasks, d-TBCNN outperforms previous state-of-the-art results, whereas in the sentence matching task, d-TBCNN achieves comparable performance to the previous state-of-the-art model, which has a higher matching complexity.]

Published: Oct 2, 2018

Keywords: Tree-based convolution; Dependency parsing; Sentence modeling; Sentence matching

There are no references for this article.