Image-based Text Classification using 2D Convolutional Neural Networks
| Autor: | Dimitrios Tzovaras, Dimitrios Giakoumis, Liming Chen, Joahannes Kroph, Erinc Merdivan, Matthieu Geist, Anastasios Vafeiadis, Raouf Hamzaoui, Dimitrios Kalatzis, Konstantinos Votis, Sten Hanke |
|---|---|
| Přispěvatelé: | Machine Learning and Computational Biology (ABC), Department of Algorithms, Computation, Image and Geometry (LORIA - ALGO), Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS), Austrian Institute of Technology [Vienna] (AIT), Information Technologies Institute (ITI), De Montfort University [Leicester, United Kingdom] (DMU), Laboratoire Interdisciplinaire des Environnements Continentaux (LIEC), Institut national des sciences de l'Univers (INSU - CNRS)-Observatoire Terre et Environnement de Lorraine (OTELo), Institut national des sciences de l'Univers (INSU - CNRS)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut national des sciences de l'Univers (INSU - CNRS)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut Ecologie et Environnement (INEE), Centre National de la Recherche Scientifique (CNRS)-Centre National de la Recherche Scientifique (CNRS), Institut Ecologie et Environnement (INEE), Centre National de la Recherche Scientifique (CNRS)-Centre National de la Recherche Scientifique (CNRS)-Institut national des sciences de l'Univers (INSU - CNRS)-Observatoire Terre et Environnement de Lorraine (OTELo), Institut national des sciences de l'Univers (INSU - CNRS)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut national des sciences de l'Univers (INSU - CNRS)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS) |
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
050101 languages & linguistics
Computer science Convolutional Neural Network 02 engineering and technology Semantics computer.software_genre Convolutional neural network Dialog modeling Image (mathematics) Task (project management) [STAT.ML]Statistics [stat]/Machine Learning [stat.ML] 0202 electrical engineering electronic engineering information engineering 0501 psychology and cognitive sciences Dialog box Natural Language Processing business.industry Deep learning 05 social sciences Optical character recognition Text classification 020201 artificial intelligence & image processing Artificial intelligence business computer Natural language processing Image based |
| Zdroj: | 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) 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), Aug 2019, Leicester, United Kingdom. pp.144-149, ⟨10.1109/SmartWorld-UIC-ATC-SCALCOM-IOP-SCI.2019.00066⟩ SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI |
| DOI: | 10.1109/SmartWorld-UIC-ATC-SCALCOM-IOP-SCI.2019.00066⟩ |
| Popis: | International audience; We propose a new approach to text classificationin which we consider the input text as an image and apply2D Convolutional Neural Networks to learn the local andglobal semantics of the sentences from the variations of thevisual patterns of words. Our approach demonstrates thatit is possible to get semantically meaningful features fromimages with text without using optical character recognitionand sequential processing pipelines, techniques that traditionalnatural language processing algorithms require. To validateour approach, we present results for two applications: textclassification and dialog modeling. Using a 2D ConvolutionalNeural Network, we were able to outperform the state-of-art accuracy results for a Chinese text classification task andachieved promising results for seven English text classificationtasks. Furthermore, our approach outperformed the memorynetworks without match types when using out of vocabularyentities from Task 4 of the bAbI dialog dataset. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|