Fully Convolutional Networks for Text Classification
Machine Learning
2019-02-18 v1 Machine Learning
Abstract
In this work I propose a new way of using fully convolutional networks for classification while allowing for input of any size. I additionally propose two modifications on the idea of attention and the benefits and detriments of using the modifications. Finally, I show suboptimal results on the ITAmoji 2018 tweet to emoji task and provide a discussion about why that might be the case as well as a proposed fix to further improve results.
Keywords
Cite
@article{arxiv.1902.05575,
title = {Fully Convolutional Networks for Text Classification},
author = {Jacob Anderson},
journal= {arXiv preprint arXiv:1902.05575},
year = {2019}
}
Comments
6 pages, 4 tables, 3 figures, submitted for the EVALITA 2018 workshop as part of clic-it 2018 conference