Deep Convolution Neural Network for Extreme Multi-label Text Classification

@inproceedings{Gargiulo2018DeepCN,
  title={Deep Convolution Neural Network for Extreme Multi-label Text Classification},
  author={Francesco Gargiulo and Stefano Silvestri and Mario Ciampi},
  booktitle={HEALTHINF},
  year={2018}
}
In this paper we present an analysis on the usage of Deep Neural Networks for extreme multi-label and multiclass text classification. [] Key Result All the result will be evaluated using the PubMed scientific articles collection as
View via Publisher
scitepress.org
14 Citations
Background Citations
1
Methods Citations
2
Results Citations
1

Figures and Tables from this paper

14 Citations

Citation Type

Citation Type

Deep neural network for hierarchical extreme multi-label text classification
ML-Net: multi-label classification of biomedical texts with deep neural networks
OBJECTIVE In multi-label text classification, each textual document is assigned 1 or more labels. As an important task that has broad applications in biomedicine, a number of different computational…
GHS-NET a generic hybridized shallow neural network for multi-label biomedical text classification
Exploit Hierarchical Label Knowledge for Deep Learning
TLDR
A methodology based on a complex deep learning network topology, named Hierarchical Deep Neural Network (HDNN), applied to eXtreme Multi-label Text Classification (XMTC) problem shows a slight performance improvement, with respect to a classical approach based on Convolution Neural Network.
InPHYNet: Leveraging attention-based multitask recurrent networks for multi-label physics text classification
Multi-class railway complaints categorization using Neural Networks: RailNeural
Analysis Classification Opinion of Policy Government Announces Cabinet Reshuffle on YouTube Comments Using 1D Convolutional Neural Networks
TLDR
From the results of this study, classification can be done very well with the CNN model and accuracy by using variations of epoch 10, 30, 150, and 300 with the best results of 100%, loss, and accuracy with the Naïve Bayes 93% and CNN methods.
Text Classification Using LDA-W2V Hybrid Algorithm
TLDR
A hybrid approach making use of well-examined Latent Dirichlet Allocation algorithm expanded by the knowledge acquired via word embeddings representing words is proposed.
Deep learning for natural language processing of free-text pathology reports: a comparison of learning curves
TLDR
This open-source framework enables the development of high-performing and fast learning natural language processing models that could accelerate retrospective chart review, assemble clinical registries and facilitate a rapid learning healthcare system.
Incorporating Figure Captions and Descriptive Text in MeSH Term Indexing
TLDR
A novel multichannel TextCNN model for MeSH term indexing is presented and it is demonstrated that figure and table captions, as well as paragraphs associated with the figures and tables, are important feature sources for the method.
...
1
2
...

References

SHOWING 1-10 OF 36 REFERENCES
Deep Learning for Extreme Multi-label Text Classification
TLDR
This paper presents the first attempt at applying deep learning to XMTC, with a family of new Convolutional Neural Network models which are tailored for multi-label classification in particular.
Large-Scale Multi-label Text Classification - Revisiting Neural Networks
TLDR
It is shown that BP-MLL's ranking loss minimization can be efficiently and effectively replaced with the commonly used cross entropy error function, and that several advances in neural network training that have been developed in the realm of deep learning can be effectively employed in this setting.
Ensemble application of convolutional and recurrent neural networks for multi-label text categorization
TLDR
This paper proposes an ensemble application of convolutional and recurrent neural networks to capture both the global and the local textual semantics and to model high-order label correlations while having a tractable computational complexity.
Large Scale Multi-label Text Classification with Semantic Word Vectors
TLDR
This work explores how both a convolutional neural network and a recurrent network with a gated recurrent unit (GRU) can independently be used with pre-trained word2vec embeddings to solve a large scale multi-label text classification problem.
Very Deep Convolutional Networks for Text Classification
TLDR
This work presents a new architecture (VDCNN) for text processing which operates directly at the character level and uses only small convolutions and pooling operations, and is able to show that the performance of this model increases with the depth.
Initializing neural networks for hierarchical multi-label text classification
TLDR
A new method for hierarchical multi-label text classification is applied that initializes a neural network model final hidden layer such that it leverages label co-occurrence relations such as hypernymy, which elegantly lends itself to hierarchical classification.
Deep Extreme Multi-label Learning
TLDR
This paper proposes a practical deep embedding method for extreme multi-label classification, which harvests the ideas of non-linear embedding and graph priors-based label space modeling simultaneously.
Learning Spatial Regularization with Image-Level Supervisions for Multi-label Image Classification
TLDR
Analysis of the learned SRN model demonstrates that it can effectively capture both semantic and spatial relations of labels for improving classification performance, and significantly outperforms state-of-the-arts and has strong generalization capability.
LF-LDA: A Topic Model for Multi-label Classification
TLDR
The experimental result on RCV1-v2 textual dataset shows that LF-LDA can outperform the other two state-of-art multi-label classifiers: Tuned SVM and L-L DA on both Macro-F1 and Micro-F 1 metrics, and the low variance also indicates LF- LDA is a robust classifier.
Deep Residual Learning for Image Recognition
TLDR
This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.
...
1
2
3
4
...