Adaptive Convolution for Text Classification

Byung-Ju Choi, Jun-Hyung Park, SangKeun Lee


Abstract
In this paper, we present an adaptive convolution for text classification to give flexibility to convolutional neural networks (CNNs). Unlike traditional convolutions which utilize the same set of filters regardless of different inputs, the adaptive convolution employs adaptively generated convolutional filters conditioned on inputs. We achieve this by attaching filter-generating networks, which are carefully designed to generate input-specific filters, to convolution blocks in existing CNNs. We show the efficacy of our approach in existing CNNs based on the performance evaluation. Our evaluation indicates that all of our baselines achieve performance improvements with adaptive convolutions as much as up to 2.6 percentage point in seven benchmark text classification datasets.
Anthology ID:
N19-1256
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2475–2485
URL:
https://www.aclweb.org/anthology/N19-1256
DOI:
10.18653/v1/N19-1256
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
https://www.aclweb.org/anthology/N19-1256.pdf
Software:
 N19-1256.Software.zip