Image-Based Text Classification using 2D Convolutional Neural Networks

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.

[1]  Kevin Barraclough,et al.  I and i , 2001, BMJ : British Medical Journal.

[2]  Vinicius Fernandes de Sousa,et al.  A Data Augmentation Methodology to Improve Age Estimation Using Convolutional Neural Networks , 2016, 2016 29th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI).

[3]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[4]  Joelle Pineau,et al.  On the Evaluation of Dialogue Systems with Next Utterance Classification , 2016, SIGDIAL Conference.

[5]  Jason Weston,et al.  Memory Networks , 2014, ICLR.

[6]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Christopher D. Manning,et al.  Effective Approaches to Attention-based Neural Machine Translation , 2015, EMNLP.

[8]  Jason Weston,et al.  A unified architecture for natural language processing: deep neural networks with multitask learning , 2008, ICML '08.

[9]  Joelle Pineau,et al.  A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues , 2016, AAAI.

[10]  Phil Blunsom,et al.  A Convolutional Neural Network for Modelling Sentences , 2014, ACL.

[11]  Jason Weston,et al.  Learning End-to-End Goal-Oriented Dialog , 2016, ICLR.

[12]  Peng Wang,et al.  Semantic Clustering and Convolutional Neural Network for Short Text Categorization , 2015, ACL.

[13]  Fabrizio Sebastiani,et al.  Machine learning in automated text categorization , 2001, CSUR.

[14]  Jure Leskovec,et al.  Hidden factors and hidden topics: understanding rating dimensions with review text , 2013, RecSys.

[15]  Sergey Ioffe,et al.  Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning , 2016, AAAI.

[16]  Andrew C Papanicolaou,et al.  Source localization of the N400 response in a sentence-reading paradigm using evoked magnetic fields and magnetic resonance imaging , 1997, Brain Research.

[17]  François Chollet,et al.  Xception: Deep Learning with Depthwise Separable Convolutions , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Joelle Pineau,et al.  Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models , 2015, AAAI.

[19]  Ann Copestake.  Augmented and alternative NLP techniques for augmentative and alternative communication , 1997, Workshop On Natural Language Processing For Communication Aids.

[20]  Alan Ritter,et al.  Adversarial Learning for Neural Dialogue Generation , 2017, EMNLP.

[21]  John G. Breslin,et al.  Character-level and Multi-channel Convolutional Neural Networks for Large-scale Authorship Attribution , 2016, ArXiv.

[22]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[23]  Tong Zhang,et al.  Effective Use of Word Order for Text Categorization with Convolutional Neural Networks , 2014, NAACL.

[24]  S. Cèbe,et al.  Apprendre à lire à l'école , 2006 .

[25]  Cícero Nogueira dos Santos,et al.  Deep Convolutional Neural Networks for Sentiment Analysis of Short Texts , 2014, COLING.

[26]  Ali Farhadi,et al.  Neural Speed Reading via Skim-RNN , 2017, ICLR.

[27]  Johan Bos,et al.  Semantic Tagging with Deep Residual Networks , 2016, COLING.

[28]  Jian Sun,et al.  Identity Mappings in Deep Residual Networks , 2016, ECCV.

[29]  Quoc V. Le,et al.  Learning to Skim Text , 2017, ACL.

[30]  W. Marsden.  I and J , 2012 .

[31]  Tong Zhang,et al.  Semi-supervised Convolutional Neural Networks for Text Categorization via Region Embedding , 2015, NIPS.

[32]  Jun Wang,et al.  Character-level Convolutional Network for Text Classification Applied to Chinese Corpus , 2016, ArXiv.

[33]  Jason Weston,et al.  Natural Language Processing (Almost) from Scratch , 2011, J. Mach. Learn. Res..

[34]  A. Friederici,et al.  Music, language and meaning: brain signatures of semantic processing , 2004, Nature Neuroscience.

[35]  Yann LeCun,et al.  Very Deep Convolutional Networks for Text Classification , 2016, EACL.

[36]  Zellig S. Harris,et al.  Distributional Structure , 1954 .

[37]  Neil Genzlinger.  A. and Q , 2006 .

[38]  Xiang Zhang,et al.  Character-level Convolutional Networks for Text Classification , 2015, NIPS.

[39]  Garry Tamlyn,et al.  Music , 1993 .

[40]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[41]  Yoon Kim,et al.  Convolutional Neural Networks for Sentence Classification , 2014, EMNLP.

[42]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[43]  Quoc V. Le,et al.  Learning Longer-term Dependencies in RNNs with Auxiliary Losses , 2018, ICML.

[44]  Jason Weston,et al.  End-To-End Memory Networks , 2015, NIPS.