Name
Title | ||
|---|---|---|
Chinese Short Text Classification with Mutual-Attention Convolutional Neural Networks |
Abstract | ||
|---|---|---|
AbstractThe methods based on the combination of word-level and character-level features can effectively boost performance on Chinese short text classification. A lot of works concatenate two-level features with little processing, which leads to losing feature information. In this work, we propose a novel framework called Mutual-Attention Convolutional Neural Networks, which integrates word and character-level features without losing too much feature information. We first generate two matrices with aligned information of two-level features by multiplying word and character features with a trainable matrix. Then, we stack them as a three-dimensional tensor. Finally, we generate the integrated features using a convolutional neural network. Extensive experiments on six public datasets demonstrate improved performance of our new framework over current methods. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1145/3388970 | ACM Transactions on Asian and Low-Resource Language Information Processing |
Keywords | DocType | Volume |
Short text classification, word-level and character-level, feature integration, mutual-attention, convolutional neural networks | Journal | 19 |
Issue | ISSN | Citations |
5 | 2375-4699 | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Ming Hao | 1 | 0 | 0.34 |
| Bo Xu | 2 | 241 | 36.59 |
| Jing-Yi Liang | 3 | 0 | 0.34 |
| Bo-Wen Zhang | 4 | 7 | 2.84 |
| Xu-Cheng Yin | 5 | 533 | 44.83 |