Investigating Capsule Networks with Dynamic Routing for Text Classification (2018-03-29T00:00:00.000000Z)

TL;DR

This work proposes three strategies to stabilize the dynamic routing process to alleviate the disturbance of some noise capsules which may contain “background” information or have not been successfully trained.

Abstract

In this study, we explore capsule networks with dynamic routing for text classification. We propose three strategies to stabilize the dynamic routing process to alleviate the disturbance of some noise capsules which may contain “background” information or have not been successfully trained. A series of experiments are conducted with capsule networks on six text classification benchmarks. Capsule networks achieve state of the art on 4 out of 6 datasets, which shows the effectiveness of capsule networks for text classification. We additionally show that capsule networks exhibit significant improvement when transfer single-label to multi-label text classification over strong baseline methods. To the best of our knowledge, this is the first work that capsule networks have been empirically investigated for text modeling.

Authors

Zhou Zhao

12 papers

Jianbo Ye

2 papers

Wei Zhao

4 papers

TL;DR

Abstract

Authors

References30 items

Fast dynamic routing based on weighted kernel density estimation

Matrix capsules with EM routing

Capsule Network Performance on Complex Data

Dynamic Routing Between Capsules

Contextual Bidirectional Long Short-Term Memory Recurrent Neural Network Language Models: A Generative Approach to Sentiment Analysis

Bag of Tricks for Efficient Text Classification

Very Deep Convolutional Networks for Text Classification

Character-level Convolutional Networks for Text Classification

From Word Embeddings To Document Distances

Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks

GloVe: Global Vectors for Word Representation

Convolutional Neural Networks for Sentence Classification

Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation

Distributed Representations of Words and Phrases and their Compositionality

Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank

Transforming Auto-Encoders

TFIDF, LSI and multi-word in information retrieval and text categorization

Supervised Topic Models

Large-Scale Bayesian Logistic Regression for Text Categorization

Seeing Stars: Exploiting Class Relationships for Sentiment Categorization with Respect to Rating Scales

Mining and summarizing customer reviews

A Sentimental Education: Sentiment Analysis Using Subjectivity Summarization Based on Minimum Cuts

Learning Question Classifiers

Text Categorization with Support Vector Machines: Learning with Many Relevant Features

An evaluation of phrasal and clustered representations on a text categorization task

Determining Gains Acquired from Word Embedding Quantitatively Using Discrete Distribution Clustering

A Literature Survey on Algorithms for Multi-label Learning

Latent Dirichlet Allocation

Text categorization

A comparison of event models for naive bayes text classification

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names