Convolutional Neural Networks for Sentence Classification

Published in

Conference on Empirical Methods in Natural Lang...(2014)

External Links:

Generate Graph DownloadPDF

TL;DR

The CNN models discussed herein improve upon the state of the art on 4 out of 7 tasks, which include sentiment analysis and question classification, and are proposed to allow for the use of both task-specific and static vectors.

Abstract

We report on a series of experiments with convolutional neural networks (CNN) trained on top of pre-trained word vectors for sentence-level classification tasks. We show that a simple CNN with little hyperparameter tuning and static vectors achieves excellent results on multiple benchmarks. Learning task-specific vectors through fine-tuning offers further gains in performance. We additionally propose a simple modification to the architecture to allow for the use of both task-specific and static vectors. The CNN models discussed herein improve upon the state of the art on 4 out of 7 tasks, which include sentiment analysis and question classification.

Authors

Yoon Kim

5 papers

References33 items

Semantic Parsing for Single-Relation Question Answering

Context-aware Learning for Sentence-level Sentiment Analysis with Posterior Regularization

Political Ideology Detection Using Recursive Neural Networks

Distributed Representations of Sentences and Documents

A Convolutional Neural Network for Modelling Sentences

Convolutional Neural Networks for Sentence Classification

Published in

Conference on Empirical Methods in Natural Lang...(2014)

External Links:

Generate Graph DownloadPDF

TL;DR

Abstract

Authors

Yoon Kim

5 papers

References33 items

Semantic Parsing for Single-Relation Question Answering

Context-aware Learning for Sentence-level Sentiment Analysis with Posterior Regularization

Political Ideology Detection Using Recursive Neural Networks

Distributed Representations of Sentences and Documents

A Convolutional Neural Network for Modelling Sentences

Learning semantic representations using convolutional neural networks for web search

CNN Features Off-the-Shelf: An Astounding Baseline for Recognition

A Statistical Parsing Framework for Sentiment Classification

Distributed Representations of Words and Phrases and their Compositionality

Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank

The Role of Syntax in Vector Space Models of Compositional Semantics

Fast dropout training

Speech recognition with deep recurrent neural networks

ADADELTA: An Adaptive Learning Rate Method

ImageNet classification with deep convolutional neural networks

Semantic Compositionality through Recursive Matrix-Vector Spaces

Baselines and Bigrams: Simple, Good Sentiment and Topic Classification

Improving neural networks by preventing co-adaptation of feature detectors

Semi-Supervised Recursive Autoencoders for Predicting Sentiment Distributions

Learning Discriminative Projections for Text Similarity Measures

Natural Language Processing (Almost) from Scratch

Adaptive Subgradient Methods for Online Learning and Stochastic Optimization

From symbolic to sub-symbolic information in question classification

Dependency Tree-based Sentiment Classification using CRFs with Hidden Variables

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

A neural probabilistic language model

Learning Question Classifiers

Recurrent architectures, though difficult to train, seem promising for sentence composition/classification Sutsekever et al., Sequence to Sequence Learning with Neural Networks, arXiv 2014

TL;DR

Abstract

Authors

References33 items

Semantic Parsing for Single-Relation Question Answering

Context-aware Learning for Sentence-level Sentiment Analysis with Posterior Regularization

Political Ideology Detection Using Recursive Neural Networks

Distributed Representations of Sentences and Documents

A Convolutional Neural Network for Modelling Sentences

TL;DR

Abstract

Authors

References33 items

Semantic Parsing for Single-Relation Question Answering

Context-aware Learning for Sentence-level Sentiment Analysis with Posterior Regularization

Political Ideology Detection Using Recursive Neural Networks

Distributed Representations of Sentences and Documents

A Convolutional Neural Network for Modelling Sentences

Learning semantic representations using convolutional neural networks for web search

CNN Features Off-the-Shelf: An Astounding Baseline for Recognition

A Statistical Parsing Framework for Sentiment Classification

Distributed Representations of Words and Phrases and their Compositionality

Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank

The Role of Syntax in Vector Space Models of Compositional Semantics

Fast dropout training

Speech recognition with deep recurrent neural networks

ADADELTA: An Adaptive Learning Rate Method

ImageNet classification with deep convolutional neural networks

Semantic Compositionality through Recursive Matrix-Vector Spaces

Baselines and Bigrams: Simple, Good Sentiment and Topic Classification

Improving neural networks by preventing co-adaptation of feature detectors

Semi-Supervised Recursive Autoencoders for Predicting Sentiment Distributions

Learning Discriminative Projections for Text Similarity Measures

Natural Language Processing (Almost) from Scratch

Adaptive Subgradient Methods for Online Learning and Stochastic Optimization

From symbolic to sub-symbolic information in question classification

Dependency Tree-based Sentiment Classification using CRFs with Hidden Variables

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

A neural probabilistic language model

Learning Question Classifiers

Recurrent architectures, though difficult to train, seem promising for sentence composition/classification Sutsekever et al., Sequence to Sequence Learning with Neural Networks, arXiv 2014

Annotating Expressions of Opinions and Emotions in Language

Gradient-based learning applied to document recognition

Document-level classification

Field of Study

Venue Information

Name

Type

URL

Alternate Names