Image-Based Text Classification using 2D Convolutional Neural Networks

Erinc Merdivan, Anastasios Vafeiadis, Dimitrios Kalatzis, Sten Hanke, Joahannes Kroph, Konstantinos Votis, Dimitrios Giakoumis, Dimitrios Tzovaras, Liming Chen, Raouf Hamzaoui, Matthieu Geist

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We 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-of-art 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.
Original languageEnglish
Title of host publicationProceedings - 2019 IEEE SmartWorld, Ubiquitous Intelligence and Computing, Advanced and Trusted Computing, Scalable Computing and Communications, Internet of People and Smart City Innovation, SmartWorld/UIC/ATC/SCALCOM/IOP/SCI 2019
Place of PublicationLeicester, United Kingdom
PublisherIEEE Xplore
Pages144-149
Number of pages6
ISBN (Electronic)978-1-7281-4034-6
ISBN (Print)978-1-7281-4035-3
DOIs
Publication statusPublished - 9 Apr 2020
Event2019 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation(SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI) - Leicester, United Kingdom
Duration: 19 Aug 201923 Aug 2019

Publication series

NameProceedings - 2019 IEEE SmartWorld, Ubiquitous Intelligence and Computing, Advanced and Trusted Computing, Scalable Computing and Communications, Internet of People and Smart City Innovation, SmartWorld/UIC/ATC/SCALCOM/IOP/SCI 2019

Conference

Conference2019 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation(SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI)
Period19/08/1923/08/19

Keywords

  • Convolutional neural networks
  • Deep learning
  • Dialogue modelling
  • Text classification

Fingerprint Dive into the research topics of 'Image-Based Text Classification using 2D Convolutional Neural Networks'. Together they form a unique fingerprint.

  • Cite this

    Merdivan, E., Vafeiadis, A., Kalatzis, D., Hanke, S., Kroph, J., Votis, K., Giakoumis, D., Tzovaras, D., Chen, L., Hamzaoui, R., & Geist, M. (2020). Image-Based Text Classification using 2D Convolutional Neural Networks. In Proceedings - 2019 IEEE SmartWorld, Ubiquitous Intelligence and Computing, Advanced and Trusted Computing, Scalable Computing and Communications, Internet of People and Smart City Innovation, SmartWorld/UIC/ATC/SCALCOM/IOP/SCI 2019 (pp. 144-149). [9060337] (Proceedings - 2019 IEEE SmartWorld, Ubiquitous Intelligence and Computing, Advanced and Trusted Computing, Scalable Computing and Communications, Internet of People and Smart City Innovation, SmartWorld/UIC/ATC/SCALCOM/IOP/SCI 2019). IEEE Xplore. https://doi.org/10.1109/SmartWorld-UIC-ATC-SCALCOM-IOP-SCI.2019.00066