# Multichannel Variable-Size Convolution for Sentence Classification

arXiv: https://arxiv.org/abs/1603.04513 · HTML: https://mlsanity.com/paper/1603.04513/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Mar 2016.

## Built on by (most cited first, 5 of 5)

- [Dual Transformer for Point Cloud Analysis](https://mlsanity.com/paper/2104.13044/) (2021)
- [Machine Learning (ML)-Centric Resource Management in Cloud Computing: A Review and Future Directions](https://mlsanity.com/paper/2105.05079/) (2021)
- [Deep Learning-based Sentiment Classification: A Comparative Survey](https://mlsanity.com/paper/2312.17253/) (2023)
- [Feature engineering vs. deep learning for paper section identification: Toward applications in Chinese medical literature](https://mlsanity.com/paper/2412.11125/) (2024)
- [Arabic Text Sentiment Analysis: Reinforcing Human-Performed Surveys with Wider Topic Analysis](https://mlsanity.com/paper/2403.01921/) (2024)

## Abstract (arXiv)

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.