Dependency sensitive convolutional neural networks for modeling sentences and documents

Rui Zhang, Honglak Lee, Dragomir Radev

Research output: Chapter in Book/Report/Conference proceedingConference contribution

85 Scopus citations

Abstract

The goal of sentence and document modeling is to accurately represent the meaning of sentences and documents for various Natural Language Processing tasks. In this work, we present Dependency Sensitive Convolutional Neural Networks (DSCNN) as a generalpurpose classification system for both sentences and documents. DSCNN hierarchically builds textual representations by processing pretrained word embeddings via Long Short- Term Memory networks and subsequently extracting features with convolution operators. Compared with existing recursive neural models with tree structures, DSCNN does not rely on parsers and expensive phrase labeling, and thus is not restricted to sentencelevel tasks. Moreover, unlike other CNNbased models that analyze sentences locally by sliding windows, our system captures both the dependency information within each sentence and relationships across sentences in the same document. Experiment results demonstrate that our approach is achieving state-ofthe-art performance on several tasks, including sentiment analysis, question type classification, and subjectivity classification.

Original languageEnglish (US)
Title of host publication2016 Conference of the North American Chapter of the Association for Computational Linguistics
Subtitle of host publicationHuman Language Technologies, NAACL HLT 2016 - Proceedings of the Conference
PublisherAssociation for Computational Linguistics (ACL)
Pages1512-1521
Number of pages10
ISBN (Electronic)9781941643914
DOIs
StatePublished - 2016
Event15th Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - San Diego, United States
Duration: Jun 12 2016Jun 17 2016

Publication series

Name2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference

Conference

Conference15th Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016
Country/TerritoryUnited States
CitySan Diego
Period6/12/166/17/16

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Linguistics and Language
  • Language and Linguistics

Fingerprint

Dive into the research topics of 'Dependency sensitive convolutional neural networks for modeling sentences and documents'. Together they form a unique fingerprint.

Cite this