Fully Convolutional Networks for Text Classification

TL;DR

This paper introduces a novel approach using fully convolutional networks for text classification, exploring attention modifications, and analyzing their effects on performance with discussions on limitations and future improvements.

Contribution

It presents a new application of fully convolutional networks for variable-sized text classification and evaluates attention modifications with insights into their impact.

Findings

Suboptimal results on ITAmoji 2018 dataset

Analysis of attention modification effects

Discussion on potential improvements

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.