Convolutional Neural Networks for Sentence Classification

@inproceedings{Kim2014ConvolutionalNN,
  title={Convolutional Neural Networks for Sentence Classification},
  author={Yoon Kim},
  booktitle={EMNLP},
  year={2014}
}
  • Yoon Kim
  • Published in EMNLP 2014
  • Computer Science
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. [...] Key Method 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.Expand
Effect of parameter variations on accuracy of Convolutional Neural Network
TLDR
From the observations, it is demonstrated that a fairly less-complex CNN that has a small amount of parameter adjustments and fine-tuning can achieve a significant growth in performance. Expand
An analysis of convolutional neural networks for sentence classification
TLDR
A series of experiments with Convolutional Neural Networks for sentence-level classification tasks with different hyperparameter settings and how sensitive model performance is to changes in these configurations are shown. Expand
A Comparative Study of Neural Network Models for Sentence Classification
This paper presents an extensive comparative study of four neural network models, including feed-forward networks, convolutional networks, recurrent networks and long short-term memory networks, onExpand
Dependency-based Convolutional Neural Networks for Sentence Embedding
TLDR
This work proposes a tree-based convolutional neural network model which exploit various long-distance relationships between words, which improves the sequential baselines on all three sentiment and question classification tasks, and achieves the highest published accuracy on TREC. Expand
Convolutional Neural Networks for Sentiment Classification on Business Reviews
TLDR
This paper presents the approach on the task of classifying business reviews using word embeddings on a large-scale dataset provided by Yelp: Yelp 2017 challenge dataset, and compares word-based CNN using several pre-trained wordembeddings and end-to-end vector representations for text reviews classification. Expand
Accuracy of Convolution Neural Networks for Classifying Sentiments on Movie Reviews
TLDR
This paper presents the approach on the task of classifying movie reviews using the word embedding on a large-scale dataset provided by Stanford, and compares the accuracy of word-based CNN models for different kernel sizes with structured and unstructured sentences. Expand
A C-LSTM Neural Network for Text Classification
TLDR
C-LSTM is a novel and unified model for sentence representation and text classification that outperforms both CNN and LSTM and can achieve excellent performance on these tasks. Expand
Do Convolutional Networks need to be Deep for Text Classification ?
TLDR
This work shows on 5 standard text classification and sentiment analysis tasks that deep models indeed give better performances than shallow networks when the text input is represented as a sequence of characters, but a simple shallow-and-wide network outperforms deep models such as DenseNet with word inputs. Expand
Attention-Based Convolutional Neural Networks for Sentence Classification
TLDR
This paper proposes a novel convolutional neural network with attention mechanism to improve the performance of sentence classification and demonstrates that the proposed model significantly outperforms the traditional CNN model and achieves competitive performance with the ones that exploit rich syntactic features. Expand
Deep Neural Network Architecture for Character-Level Learning on Short Text
TLDR
The authors' experimental results show tweets need network architectures compatible with their short length, and networks found effective for other sentiment classification tasks may not produce an effective classifier in this domain, if their architecture is ill-suited for short instances. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 34 REFERENCES
A Convolutional Neural Network for Modelling Sentences
TLDR
A convolutional architecture dubbed the Dynamic Convolutional Neural Network (DCNN) is described that is adopted for the semantic modelling of sentences and induces a feature graph over the sentence that is capable of explicitly capturing short and long-range relations. Expand
Semi-Supervised Recursive Autoencoders for Predicting Sentiment Distributions
TLDR
A novel machine learning framework based on recursive autoencoders for sentence-level prediction of sentiment label distributions that outperform other state-of-the-art approaches on commonly used datasets, without using any pre-defined sentiment lexica or polarity shifting rules. Expand
Learning semantic representations using convolutional neural networks for web search
TLDR
This paper presents a series of new latent semantic models based on a convolutional neural network to learn low-dimensional semantic vectors for search queries and Web documents that significantly outperforms other se-mantic models in retrieval performance. Expand
Baselines and Bigrams: Simple, Good Sentiment and Topic Classification
TLDR
It is shown that the inclusion of word bigram features gives consistent gains on sentiment analysis tasks, and a simple but novel SVM variant using NB log-count ratios as feature values consistently performs well across tasks and datasets. Expand
Natural Language Processing (Almost) from Scratch
We propose a unified neural network architecture and learning algorithm that can be applied to various natural language processing tasks including part-of-speech tagging, chunking, named entityExpand
Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank
TLDR
A Sentiment Treebank that includes fine grained sentiment labels for 215,154 phrases in the parse trees of 11,855 sentences and presents new challenges for sentiment compositionality, and introduces the Recursive Neural Tensor Network. Expand
Improving neural networks by preventing co-adaptation of feature detectors
When a large feedforward neural network is trained on a small training set, it typically performs poorly on held-out test data. This "overfitting" is greatly reduced by randomly omitting half of theExpand
ImageNet classification with deep convolutional neural networks
TLDR
A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective. Expand
Context-aware Learning for Sentence-level Sentiment Analysis with Posterior Regularization
TLDR
A novel context-aware method for analyzing sentiment at the level of individual sentences that encoding intuitive lexical and discourse knowledge as expressive constraints and integrating them into the learning of conditional random field models via posterior regularization is proposed. Expand
Speech recognition with deep recurrent neural networks
TLDR
This paper investigates deep recurrent neural networks, which combine the multiple levels of representation that have proved so effective in deep networks with the flexible use of long range context that empowers RNNs. Expand
...
1
2
3
4
...