Multichannel Variable-Size Convolution for Sentence Classification
arXiv:1603.04513
Abstract
We propose MVCNN, a convolution neural network (CNN) architecture for sentence classification. It (i) combines diverse versions of pretrained word embeddings and (ii) extracts features of multigranular phrases with variable-size convolution filters. We also show that pretraining MVCNN is critical for good performance. MVCNN achieves state-of-the-art performance on four tasks: on small-scale binary, small-scale multi-class and largescale Twitter sentiment prediction and on subjectivity classification.
in Proceeding of CoNLL2015
References in corpus (7)
- Efficient Estimation of Word Representations in Vector Space
- Improving neural networks by preventing co-adaptation of feature detectors
- Natural Language Processing (almost) from Scratch
- A Convolutional Neural Network for Modelling Sentences
- Modelling, Visualising and Summarising Documents with a Single Convolutional Neural Network
- The Expressive Power of Word Embeddings
- Not All Neural Embeddings are Born Equal
Cited by in corpus (9)
- Combining Convolution and Recursive Neural Networks for Sentiment Analysis
- Multichannel CNN with Attention for Text Classification
- Densely Connected Bidirectional LSTM with Applications to Sentence Classification
- Learning Semantically Coherent and Reusable Kernels in Convolution Neural Nets for Sentence Classification
- Benchmark Performance of Machine And Deep Learning Based Methodologies for Urdu Text Document Classification
- Text Classification based on Multi-granularity Attention Hybrid Neural Network
- Semantic Relatedness Based Re-ranker for Text Spotting
- Self-Balanced Dropout
- CRNN: A Joint Neural Network for Redundancy Detection