# Multichannel CNN with Attention for Text Classification

arXiv: https://arxiv.org/abs/2006.16174 · HTML: https://mlsanity.com/paper/2006.16174/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jun 2020.

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

- [A transformer based approach for fighting COVID-19 fake news](https://mlsanity.com/paper/2101.12027/) (2021)
- [TextConvoNet:A Convolutional Neural Network based Architecture for Text Classification](https://mlsanity.com/paper/2203.05173/) (2022)
- [An Attention Ensemble Approach for Efficient Text Classification of Indian Languages](https://mlsanity.com/paper/2102.10275/) (2021)
- [SECNN: Squeeze-and-Excitation Convolutional Neural Network for Sentence Classification](https://mlsanity.com/paper/2312.06088/) (2023)
- [Multichannel LSTM-CNN for Telugu Technical Domain Identification](https://mlsanity.com/paper/2102.12179/) (2021)

## Abstract (arXiv)

Recent years, the approaches based on neural networks have shown remarkable potential for sentence modeling. There are two main neural network structures: recurrent neural network (RNN) and convolution neural network (CNN). RNN can capture long term dependencies and store the semantics of the previous information in a fixed-sized vector. However, RNN is a biased model and its ability to extract global semantics is restricted by the fixed-sized vector. Alternatively, CNN is able to capture n-gram features of texts by utilizing convolutional filters. But the width of convolutional filters restricts its performance. In order to combine the strengths of the two kinds of networks and alleviate their shortcomings, this paper proposes Attention-based Multichannel Convolutional Neural Network (AMCNN) for text classification. AMCNN utilizes a bi-directional long short-term memory to encode the history and future information of words into high dimensional representations, so that the information of both the front and back of the sentence can be fully expressed. Then the scalar attention and vectorial attention are applied to obtain multichannel representations. The scalar attention can calculate the word-level importance and the vectorial attention can calculate the feature-level importance. In the classification task, AMCNN uses a CNN structure to cpture word relations on the representations generated by the scalar and vectorial attention mechanism instead of calculating the weighted sums. It can effectively extract the n-gram features of the text. The experimental results on the benchmark datasets demonstrate that AMCNN achieves better performance than state-of-the-art methods. In addition, the visualization results verify the semantic richness of multichannel representations.