Multi-Label Text Classification using Attention-based Graph Neural Network (2020-03-22T00:00:00.000000Z)

TL;DR

A graph attention network-based model is proposed to capture the attentive dependency structure among the labels in Multi-Label Text Classification to achieve similar or better performance compared to the previous state-of-the-art models.

Abstract

In Multi-Label Text Classification (MLTC), one sample can belong to more than one class. It is observed that most MLTC tasks, there are dependencies or correlations among labels. Existing methods tend to ignore the relationship among labels. In this paper, a graph attention network-based model is proposed to capture the attentive dependency structure among the labels. The graph attention network uses a feature matrix and a correlation matrix to capture and explore the crucial dependencies between the labels and generate classifiers for the task. The generated classifiers are applied to sentence feature vectors obtained from the text feature extraction network (BiLSTM) to enable end-to-end training. Attention allows the system to assign different weights to neighbor nodes per label, thus allowing it to learn the dependencies among labels implicitly. The results of the proposed model are validated on five real-world MLTC datasets. The proposed model achieves similar or better performance compared to the previous state-of-the-art models.

Authors

Ankit Pal

3 papers

Malaikannan Sankarasubbu

3 papers

M. Selvakumar

1 papers

TL;DR

Abstract

Authors

References54 items

BERT for Sequence-to-Sequence Multi-label Text Classification

Hierarchical Text Classification with Reinforced Label Assignment

Hierarchical Transfer Learning for Multi-label Text Classification

Hierarchical Taxonomy-Aware and Attentional Graph Capsule RCNNs for Large-Scale Multi-Label Text Classification

Neural Message Passing for Multi-Label Classification

Multi-Label Image Recognition With Graph Convolutional Networks

Graph Convolutional Neural Networks for Web-Scale Recommender Systems

Large-Scale Hierarchical Text Classification with Recursively Regularized Deep Graph-CNN

Bi-Directional Block Self-Attention for Fast and Memory-Efficient Sequence Modeling

Investigating Capsule Networks with Dynamic Routing for Text Classification

Binary relevance for multi-label learning: an overview

Protein Interface Prediction using Graph Convolutional Networks

Graph Attention Networks

A Comprehensive Survey of Graph Embedding: Problems, Techniques, and Applications

Deep Learning for Extreme Multi-label Text Classification

Attention is All you Need

Ensemble application of convolutional and recurrent neural networks for multi-label text categorization

Neural Sentiment Classification with User and Product Attention

Semi-Supervised Classification with Graph Convolutional Networks

Hierarchical Attention Networks for Document Classification

Hierarchical Attention Networks

Very Deep Convolutional Networks for Text Classification

Hierarchical Bayesian Inference and Recursive Regularization for Large-Scale Classification

Recurrent Convolutional Neural Networks for Text Classification

Effective Use of Word Order for Text Categorization with Convolutional Neural Networks

GloVe: Global Vectors for Word Representation

Convolutional Neural Networks for Sentence Classification

Multilabel Prediction with Probability Sets: The Hamming Loss Case

Large-Scale Multi-label Text Classification - Revisiting Neural Networks

Distributed Representations of Words and Phrases and their Compositionality

Bayesian models for Large-scale Hierarchical Classification

Binary relevance efficacy for multilabel classification

Hierarchical Classification via Orthogonal Transfer

Multilabel classification with meta-level features

Understanding the difficulty of training deep feedforward neural networks

Classifier chains for multi-label classification

Support vector machines

Deep classification in large-scale text hierarchies

An analysis of the relative hardness of Reuters-21578 subsets

RCV1: A New Benchmark Collection for Text Categorization Research

Learning multi-label scene classification

A hierarchical method for multi-class support vector machines

Hierarchical text classification and evaluation

BoosTexter: A Boosting-based System for Text Categorization

Logistic regression using sas®: theory and application

C4.5: Programs for Machine Learning

Doha, Qatar

BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

A Comprehensive Survey on Graph Neural Networks

October 25-29, 2014

Multilabel Text Classification for Automated Tag Suggestion

Using TF-IDF to Determine Word Relevance in Document Queries

Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence Multi-Label Classification Using Conditional Dependency Networks

for document classiﬁcation

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names