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

doi:10.1109/SmartWorld-UIC-ATC-SCALCOM-IOP-SCI.2019.00066

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 proceeding › Conference contribution › peer-review

7 Citations (Scopus)

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 language	English
Title of host publication	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
Place of Publication	Leicester, United Kingdom
Publisher	IEEE Xplore
Pages	144-149
Number of pages	6
ISBN (Electronic)	978-1-7281-4034-6
ISBN (Print)	978-1-7281-4035-3
DOIs	https://doi.org/10.1109/SmartWorld-UIC-ATC-SCALCOM-IOP-SCI.2019.00066
Publication status	Published (in print/issue) - 9 Apr 2020
Event	2019 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 2019 → 23 Aug 2019

Publication series

Name	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

Conference

Conference	2019 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)
Period	19/08/19 → 23/08/19

Keywords

Convolutional neural networks
Deep learning
Dialogue modelling
Text classification

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/SmartWorld-UIC-ATC-SCALCOM-IOP-SCI.2019.00066

https://ieeexplore.ieee.org/document/9060337/

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). Article 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

Merdivan, Erinc ; Vafeiadis, Anastasios ; Kalatzis, Dimitrios et al. / Image-Based Text Classification using 2D Convolutional Neural Networks. 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. Leicester, United Kingdom : IEEE Xplore, 2020. pp. 144-149 (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).

@inproceedings{00ecabe372a240f9aca73441cc6beb4c,

title = "Image-Based Text Classification using 2D Convolutional Neural Networks",

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.",

keywords = "Convolutional neural networks, Deep learning, Dialogue modelling, Text classification",

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

year = "2020",

month = apr,

day = "9",

doi = "10.1109/SmartWorld-UIC-ATC-SCALCOM-IOP-SCI.2019.00066",

language = "English",

isbn = "978-1-7281-4035-3",

series = "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",

publisher = "IEEE Xplore",

pages = "144--149",

booktitle = "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",

address = "United States",

note = "2019 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) ; Conference date: 19-08-2019 Through 23-08-2019",

}

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., 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, Leicester, United Kingdom, pp. 144-149, 2019 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), 19/08/19. https://doi.org/10.1109/SmartWorld-UIC-ATC-SCALCOM-IOP-SCI.2019.00066

Image-Based Text Classification using 2D Convolutional Neural Networks. / Merdivan, Erinc; Vafeiadis, Anastasios; Kalatzis, Dimitrios et al.
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. Leicester, United Kingdom: IEEE Xplore, 2020. p. 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).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Image-Based Text Classification using 2D Convolutional Neural Networks

AU - Merdivan, Erinc

AU - Vafeiadis, Anastasios

AU - Kalatzis, Dimitrios

AU - Hanke, Sten

AU - Kroph, Joahannes

AU - Votis, Konstantinos

AU - Giakoumis, Dimitrios

AU - Tzovaras, Dimitrios

AU - Chen, Liming

AU - Hamzaoui, Raouf

AU - Geist, Matthieu

PY - 2020/4/9

Y1 - 2020/4/9

N2 - 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.

AB - 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.

KW - Convolutional neural networks

KW - Deep learning

KW - Dialogue modelling

KW - Text classification

UR - http://www.scopus.com/inward/record.url?scp=85083574514&partnerID=8YFLogxK

U2 - 10.1109/SmartWorld-UIC-ATC-SCALCOM-IOP-SCI.2019.00066

DO - 10.1109/SmartWorld-UIC-ATC-SCALCOM-IOP-SCI.2019.00066

M3 - Conference contribution

SN - 978-1-7281-4035-3

T3 - 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

SP - 144

EP - 149

BT - 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

PB - IEEE Xplore

CY - Leicester, United Kingdom

T2 - 2019 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)

Y2 - 19 August 2019 through 23 August 2019

ER -

Merdivan E, Vafeiadis A, Kalatzis D, Hanke S, Kroph J, Votis K et al. 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. Leicester, United Kingdom: IEEE Xplore. 2020. p. 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). doi: 10.1109/SmartWorld-UIC-ATC-SCALCOM-IOP-SCI.2019.00066

Image-Based Text Classification using 2D Convolutional Neural Networks

Abstract

Publication series

Conference

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this