TY - GEN
T1 - Convolutions Are All You Need (For Classifying Character Sequences)
AU - Wood-Doughty, Zach
AU - Andrews, Nicholas
AU - Dredze, Mark
N1 - Funding Information:
This work was in part supported by the National Institute of General Medical Sciences under grant number 5R01GM114771.
Publisher Copyright:
© 2018 Association for Computational Linguistics.
PY - 2018
Y1 - 2018
N2 - While recurrent neural networks (RNNs) are widely used for text classification, they demonstrate poor performance and slow convergence when trained on long sequences. When text is modeled as characters instead of words, the longer sequences make RNNs a poor choice. Convolutional neural networks (CNNs), although somewhat less ubiquitous than RNNs, have an internal structure more appropriate for long-distance character dependencies. To better understand how CNNs and RNNs differ in handling long sequences, we use them for text classification tasks in several character-level social media datasets. The CNN models vastly outperform the RNN models in our experiments, suggesting that CNNs are superior to RNNs at learning to classify character-level data.
AB - While recurrent neural networks (RNNs) are widely used for text classification, they demonstrate poor performance and slow convergence when trained on long sequences. When text is modeled as characters instead of words, the longer sequences make RNNs a poor choice. Convolutional neural networks (CNNs), although somewhat less ubiquitous than RNNs, have an internal structure more appropriate for long-distance character dependencies. To better understand how CNNs and RNNs differ in handling long sequences, we use them for text classification tasks in several character-level social media datasets. The CNN models vastly outperform the RNN models in our experiments, suggesting that CNNs are superior to RNNs at learning to classify character-level data.
UR - http://www.scopus.com/inward/record.url?scp=85074688859&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85074688859&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85074688859
T3 - 4th Workshop on Noisy User-Generated Text, W-NUT 2018 - Proceedings of the Workshop
SP - 208
EP - 213
BT - 4th Workshop on Noisy User-Generated Text, W-NUT 2018 - Proceedings of the Workshop
PB - Association for Computational Linguistics (ACL)
T2 - 4th Workshop on Noisy User-Generated Text, W-NUT 2018
Y2 - 1 November 2018
ER -