Spectral Graph Convolutional Networks for Part-of-Speech Tagging

  • Part-of-Speech tagging is the process of assigning words with similar grammatical properties to a part of speech (PoS). In the English language, PoS-tagging algorithms generally reach very high accuracy. This thesis undertakes the task to test against these accuracies in PoS-tagging as a qualitative measure in classification capabilities for a recently developed neural network model, called graph convolutional network (GCN). The novelty proposed in this thesis is to translate a corpus into a graph as a direct input for the GCN. The experiments in this thesis serve as a proof of concept with room for improvements.

Download full text files

  • Spectral Graph Convolutional Networks for Part-of-Speech Tagging - BA thesis

Export metadata

Metadaten
Author:Saner Demirel
URN:urn:nbn:de:kola-15080
Advisor:Steffen Staab, Lukas Schmelzeisen
Document Type:Bachelor Thesis
Language:English
Date of completion:2017/02/10
Date of publication:2017/10/05
Publishing institution:Universität Koblenz-Landau, Universitätsbibliothek
Granting institution:Universität Koblenz-Landau, Campus Koblenz, Fachbereich 4
Release Date:2017/10/05
Number of pages:v, 30
Institutes:Fachbereich 4 / Institut für Computervisualistik
Licence (German):License LogoEs gilt das deutsche Urheberrecht: § 53 UrhG