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.
Verfasserangaben: | Saner Demirel |
---|---|
URN: | urn:nbn:de:kola-15080 |
Betreuer: | Steffen Staab, Lukas Schmelzeisen |
Dokumentart: | Bachelorarbeit |
Sprache: | Englisch |
Datum der Fertigstellung: | 10.02.2017 |
Datum der Veröffentlichung: | 05.10.2017 |
Veröffentlichende Institution: | Universität Koblenz, Universitätsbibliothek |
Titel verleihende Institution: | Universität Koblenz, Fachbereich 4 |
Datum der Freischaltung: | 05.10.2017 |
Seitenzahl: | v, 30 |
Institute: | Fachbereich 4 / Institut für Computervisualistik |
Lizenz (Deutsch): | Es gilt das deutsche Urheberrecht: § 53 UrhG |