Efficient Character-level Document Classification by Combining Convolution and Recurrent Layers

02/01/2016
by   Yijun Xiao, et al.
0

Document classification tasks were primarily tackled at word level. Recent research that works with character-level inputs shows several benefits over word-level approaches such as natural incorporation of morphemes and better handling of rare words. We propose a neural network architecture that utilizes both convolution and recurrent layers to efficiently encode character inputs. We validate the proposed model on eight large scale document classification tasks and compare with character-level convolution-only models. It achieves comparable performances with much less parameters.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/06/2016

Gated Word-Character Recurrent Language Model

We introduce a recurrent neural network language model (RNN-LM) with lon...
research
10/08/2018

End-to-End Text Classification via Image-based Embedding using Character-level Networks

For analysing and/or understanding languages having no word boundaries b...
research
08/30/2021

Exploring Multi-Tasking Learning in Document Attribute Classification

In this work, we adhere to explore a Multi-Tasking learning (MTL) based ...
research
03/17/2022

Optimal Rejection Function Meets Character Recognition Tasks

In this paper, we propose an optimal rejection method for rejecting ambi...
research
11/14/2016

Attending to Characters in Neural Sequence Labeling Models

Sequence labeling architectures use word embeddings for capturing simila...
research
08/07/2023

Keyword Spotting Simplified: A Segmentation-Free Approach using Character Counting and CTC re-scoring

Recent advances in segmentation-free keyword spotting treat this problem...
research
05/27/2019

Combating Adversarial Misspellings with Robust Word Recognition

To combat adversarial spelling mistakes, we propose placing a word recog...

Please sign up or login with your details

Forgot password? Click here to reset