Show simple item record

dc.contributor.authorMerdivan, Erinç
dc.contributor.authorVafeiadis, Anastasios
dc.contributor.authorKalatzis, Dimitrios
dc.contributor.authorHanke, Sten
dc.contributor.authorKropf, Johannes
dc.contributor.authorVotis, Konstantinos
dc.contributor.authorGiakoumis, Dimitrios
dc.contributor.authorTzovaras, Dimitrios
dc.contributor.authorChen, Liming
dc.contributor.authorHamzaoui, Raouf
dc.contributor.authorGeist, Matthieu
dc.date.accessioned2019-06-24T09:00:27Z
dc.date.available2019-06-24T09:00:27Z
dc.date.issued2019-08
dc.identifier.citationE. Merdivan, A. Vafeiadis, D. Kalatzis, S. Hanke, J. Kropf, K. Votis, D. Giakoumis, D. Tzovaras, L. Chen, R. Hamzaoui, M. Geist, Image-based text classification using 2D convolutional neural networks In: Proc. IEEE Smart World Congress 2019, Leicester, Aug. 2019.en
dc.identifier.urihttps://www.dora.dmu.ac.uk/handle/2086/18112
dc.description.abstractWe propose a new approach to text classification in which we consider the input text as an image and apply 2D Convolutional Neural Networks to learn the local and global semantics of the sentences from the variations of the visual patterns of words. Our approach demonstrates that it is possible to get semantically meaningful features from images with text without using optical character recognition and sequential processing pipelines, techniques that traditional natural language processing algorithms require. To validate our approach, we present results for two applications: text classification and dialog modeling. Using a 2D Convolutional Neural Network, we were able to outperform the state-ofart accuracy results for a Chinese text classification task and achieved promising results for seven English text classification tasks. Furthermore, our approach outperformed the memory networks without match types when using out of vocabulary entities from Task 4 of the bAbI dialog dataset.en
dc.language.isoenen
dc.publisherIEEEen
dc.subjectText classificationen
dc.subjectConvolutional Neural Networken
dc.subjectNatural Language Processingen
dc.subjectDialog modelingen
dc.titleImage-based Text Classification using 2D Convolutional Neural Networksen
dc.typeConferenceen
dc.peerreviewedYesen
dc.funderEuropean Union (EU) Horizon 2020en
dc.projectidACROSSING project, Marie Skłodowska-Curie EU Framework for Research and Innovation Horizon 2020, Grant Agreement No. 676157.en
dc.cclicenceCC-BY-NCen
dc.date.acceptance2019-05-29
dc.researchinstituteCyber Technology Institute (CTI)en


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record