Please use this identifier to cite or link to this item:
https://www.um.edu.mt/library/oar/handle/123456789/54257
Title: | Document classification using deep learning |
Authors: | Azzopardi, Keith |
Keywords: | Machine learning Classification Neural networks (Computer science) |
Issue Date: | 2019 |
Citation: | Azzopardi, K. (2019). Document classification using deep learning (Bachelor’s dissertation). |
Abstract: | This study tackles the classification of business documents into six pre-defined classes, (invoices, receipts, delivery notes, purchase orders, quotations and others). Three machine learning models, in increasing complexity, are proposed, implemented and compared. The models comprise a term frequency based classifier, a TF-IDF based Multinomial Naive Bayes classifier and a TF-IDF based Artificial Neural Network classifier. The models are trained and tested using a synthetic business document dataset, which was created as part of this project. The Neural Network classifier obtained the highest overall classification accuracy, over 97.7%, and outperformed the other two models by at least 5% points. The results show how this task benefits from the implementation of deep learning. |
Description: | B.SC.(HONS)COMPUTER ENG. |
URI: | https://www.um.edu.mt/library/oar/handle/123456789/54257 |
Appears in Collections: | Dissertations - FacICT - 2019 Dissertations - FacICTCCE - 2019 |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
19BCE004.pdf Restricted Access | 2.38 MB | Adobe PDF | View/Open Request a copy |
Items in OAR@UM are protected by copyright, with all rights reserved, unless otherwise indicated.