LGMLFeb 14, 2019

Fully Convolutional Networks for Text Classification

arXiv:1902.05575v14 citations
Originality Synthesis-oriented
AI Analysis

This work addresses text classification for social media applications, but it is incremental as it builds on existing methods with minor modifications.

The authors tackled text classification using fully convolutional networks with variable-length inputs and attention modifications, achieving suboptimal results on the ITAmoji 2018 tweet-to-emoji task and proposing a fix for improvement.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes