HDLTex: Hierarchical Deep Learning for Text Classification

By Kamran Kowsari, Donald E. Brown, Mojtaba Heidarysafa, Kiana Jafari Meimandi, Matthew S. Gerber, Laura E. Barnes. International Conference on Machine Learning and Applications, 2017

485 citations recorded by the source corpus.

Increasingly large document collections require improved information processing methods for searching, retrieving, and organizing text. Central to these information processing methods is document classification, which has become an important application for supervised learning. Recently the performance of traditional supervised classifiers has degraded as the number of documents has increased. This is because along with growth in the number of documents has come an increase in the number of categories. This paper approaches this problem differently from current document classification methods that view the problem as multi-class classification. Instead we perform hierarchical classification using an approach we call Hierarchical Deep Learning for Text classification (HDLTex). HDLTex employs stacks of deep learning architectures to provide specialized understanding at each level of the document hierarchy.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/9dfacffdae4527d01563814c804e410e4ca885e1

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

A Survey on Text Classification: From Traditional to Deep Learning (2020, methodology): “The WOS-11967 is crawled from the Web of Science, consisting of abstracts of published papers with two labels for each example.”
A Survey on Text Classification: From Shallow to Deep Learning (2020, background): “The WOS-11967 [216] is crawled from the Web of Science, consisting of abstracts of published papers with two labels for each example.”
Survey on supervised machine learning techniques for automatic text classification (2019, methodology): “A new method to hierarchical document classification like HDLTex that was combined multiple deep learning method to generate hierarchical classifications was introduced by (Kowsari et al. 2017).”
A Survey of Deep Learning: Platforms, Applications and Emerging Research Trends (2018, background): “[71] proposed a hierarchical deep learning architecture for text-based document classification, in which each deep learning model is constructed of fully connected DNN, RNN with gated recurrent units (GRUs) and LSTM, and CNN.”
Deep Learning--based Text Classification (2020, methodology): “s. The authors first apply a Bi-LSTM model to classify opinionated sentences into three types. Each group of sentences is then fed to a one-dimensional CNN separately for sentiment classification. In [128], Kowsari et al. proposed a Hierarchical Deep Learning approach for Text classification (HDLTex”
Text Classification Algorithms: A Survey (2019, background): “Deep Neural Networks Deep neural networks (DNN) are designed to learn by multi-connection of layers that every single layer only receives the connection from previous and provides connections only to the next layer in a hidden part [2].”