CLLGNEJun 6, 2016

Very Deep Convolutional Networks for Text Classification

arXiv:1606.01781v2323 citations
Originality Highly original
AI Analysis

This addresses the need for deeper architectures in text processing, offering a novel approach that could enhance performance in NLP applications.

The paper tackled the problem of shallow neural networks in NLP by introducing a very deep convolutional network (VDCNN) for text classification, achieving state-of-the-art improvements on several public tasks with up to 29 layers.

The dominant approach for many NLP tasks are recurrent neural networks, in particular LSTMs, and convolutional neural networks. However, these architectures are rather shallow in comparison to the deep convolutional networks which have pushed the state-of-the-art in computer vision. We present a new architecture (VDCNN) for text processing which operates directly at the character level and uses only small convolutions and pooling operations. We are able to show that the performance of this model increases with depth: using up to 29 convolutional layers, we report improvements over the state-of-the-art on several public text classification tasks. To the best of our knowledge, this is the first time that very deep convolutional nets have been applied to text processing.

Code Implementations24 repos

Data from Papers with Code (CC-BY-SA-4.0)

Foundations

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

Your Notes