Character-level Convolutional Networks for Text Classification
X. Zhang, J. Zhao, and Y. LeCun. Advances in Neural Information Processing Systems 28, Curran Associates, Inc., (2015)
Abstract
This article offers an empirical exploration on the use of character-level convolutional networks (ConvNets) for text classification. We constructed several large-scale datasets to show that character-level convolutional networks could achieve state-of-the-art or competitive results. Comparisons are offered against traditional models such as bag of words, n-grams and their TFIDF variants, and deep learning models such as word-based ConvNets and recurrent neural networks.
%0 Book Section
%1 zhang2015characterlevel
%A Zhang, Xiang
%A Zhao, Junbo
%A LeCun, Yann
%B Advances in Neural Information Processing Systems 28
%D 2015
%E Cortes, C.
%E Lawrence, N. D.
%E Lee, D. D.
%E Sugiyama, M.
%E Garnett, R.
%I Curran Associates, Inc.
%K classification cnn ml nips text understanding
%P 649--657
%T Character-level Convolutional Networks for Text Classification
%U http://papers.nips.cc/paper/5782-character-level-convolutional-networks-for-text-classification.pdf
%X This article offers an empirical exploration on the use of character-level convolutional networks (ConvNets) for text classification. We constructed several large-scale datasets to show that character-level convolutional networks could achieve state-of-the-art or competitive results. Comparisons are offered against traditional models such as bag of words, n-grams and their TFIDF variants, and deep learning models such as word-based ConvNets and recurrent neural networks.
@incollection{zhang2015characterlevel,
abstract = {This article offers an empirical exploration on the use of character-level convolutional networks (ConvNets) for text classification. We constructed several large-scale datasets to show that character-level convolutional networks could achieve state-of-the-art or competitive results. Comparisons are offered against traditional models such as bag of words, n-grams and their TFIDF variants, and deep learning models such as word-based ConvNets and recurrent neural networks.},
added-at = {2018-09-26T11:55:16.000+0200},
author = {Zhang, Xiang and Zhao, Junbo and LeCun, Yann},
biburl = {https://www.bibsonomy.org/bibtex/230d6b77d66b0aa0ec6f587eb76e963b0/jaeschke},
booktitle = {Advances in Neural Information Processing Systems 28},
editor = {Cortes, C. and Lawrence, N. D. and Lee, D. D. and Sugiyama, M. and Garnett, R.},
interhash = {ec817986f91d2662694825ce51f3faa8},
intrahash = {30d6b77d66b0aa0ec6f587eb76e963b0},
keywords = {classification cnn ml nips text understanding},
pages = {649--657},
publisher = {Curran Associates, Inc.},
timestamp = {2018-09-26T11:55:16.000+0200},
title = {Character-level Convolutional Networks for Text Classification},
url = {http://papers.nips.cc/paper/5782-character-level-convolutional-networks-for-text-classification.pdf},
year = 2015
}