Neural part-of-speech tagging
Please use this identifier to cite or link to this item:
http://hdl.handle.net/10045/84670
Title: | Neural part-of-speech tagging |
---|---|
Authors: | Valero Antón, Francisco de Borja |
Research Director: | Pérez-Ortiz, Juan Antonio | Sánchez-Martínez, Felipe |
Center, Department or Service: | Universidad de Alicante. Departamento de Lenguajes y Sistemas Informáticos |
Keywords: | Neural networks | Part-of-speech tagging system |
Knowledge Area: | Lenguajes y Sistemas Informáticos |
Issue Date: | 11-Dec-2018 |
Date of defense: | 29-Nov-2018 |
Abstract: | In this work, we propose the implementation of a part-of-speech tagging system using recurrent neural networks. For that purpose, initially we study the theoretical fundamentals of that kind of neural networks. Next, we propose three different architectures in order to disambiguate ambiguous words. Finally, we achieve a system able to disambiguate with a 93.5% total accuracy and with 83.2% accuracy on ambiguous words with the section of Wall Street Journal that belongs to the Penn Treebank corpus. |
URI: | http://hdl.handle.net/10045/84670 |
Language: | eng |
Type: | info:eu-repo/semantics/bachelorThesis |
Rights: | Licencia Creative Commons Reconocimiento-NoComercial-SinObraDerivada 4.0 |
Appears in Collections: | Grado en Ingeniería Informática - Trabajos Fin de Grado |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Neural_partofspeech_tagging_VALERO_ANTON_FRANCISCO_DE_BORJA.pdf | 1,61 MB | Adobe PDF | Open Preview | |
Items in RUA are protected by copyright, with all rights reserved, unless otherwise indicated.