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

Learn More →

Efficiency Analysis of Deeplearning4J Neural Network Classifiers in Development of Transition Based Dependency Parsers

Efficiency Analysis of Deeplearning4J Neural Network Classifiers in Development of Transition... AbstractDependency parsing is a complex process in natural language text processing, text to semantic transformation. The efficiency improvement of dependency parsing is a current and an active research area in the NLP community. The paper presents four transition-based dependency parser models with implementation using DL4J classifiers. The efficiency of the proposed models were tested with Hungarian language corpora. The parsing model uses a data representation form based on lightweight embedding and a novel morphological-description-vector format is proposed for the input layer. Based on the test experiments on parsing Hungarian text documents, the proposed list-based transitions parsers outperform the widespread stack-based variants. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Acta Marisiensis: Seria Technologica de Gruyter

Efficiency Analysis of Deeplearning4J Neural Network Classifiers in Development of Transition Based Dependency Parsers

Loading next page...
 
/lp/de-gruyter/efficiency-analysis-of-deeplearning4j-neural-network-classifiers-in-DeYojtLeV9

References

References for this paper are not available at this time. We will be adding them shortly, thank you for your patience.

Publisher
de Gruyter
Copyright
© 2021 László Csépányi-Fürjes et al., published by Sciendo
ISSN
2668-4217
DOI
10.2478/amset-2021-0006
Publisher site
See Article on Publisher Site

Abstract

AbstractDependency parsing is a complex process in natural language text processing, text to semantic transformation. The efficiency improvement of dependency parsing is a current and an active research area in the NLP community. The paper presents four transition-based dependency parser models with implementation using DL4J classifiers. The efficiency of the proposed models were tested with Hungarian language corpora. The parsing model uses a data representation form based on lightweight embedding and a novel morphological-description-vector format is proposed for the input layer. Based on the test experiments on parsing Hungarian text documents, the proposed list-based transitions parsers outperform the widespread stack-based variants.

Journal

Acta Marisiensis: Seria Technologicade Gruyter

Published: Jun 1, 2021

Keywords: NLP; dependency parser; word embedding; lightweight word embedding

There are no references for this article.