| Issue |
MATEC Web Conf.
Volume 309, 2020
2019 International Conference on Computer Science Communication and Network Security (CSCNS2019)
|
|
|---|---|---|
| Article Number | 03015 | |
| Number of page(s) | 8 | |
| Section | Smart Algorithms and Recognition | |
| DOI | https://doi.org/10.1051/matecconf/202030903015 | |
| Published online | 04 March 2020 | |
A multi-label text classification model based on ELMo and attention
Guangdong Power information Technology Co., Ltd. Yuedian Buliding, 6-8 Shuijun Road, Yuexiu District, Guangzhou, Guangdong, China
* Corresponding author: gaoshang8202@126.com
Text classification is a common application in natural language processing. We proposed a multi-label text classification model based on ELMo and attention mechanism which help solve the problem for the sentiment classification task that there is no grammar or writing convention in power supply related text and the sentiment related information disperses in the text. Firstly, we use pre-trained word embedding vector to extract the feature of text from the Internet. Secondly, the analyzed deep information features are weighted according to the attention mechanism. Finally, an improved ELMo model in which we replace the LSTM module with GRU module is used to characterize the text and information is classified. The experimental results on Kaggle’s toxic comment classification data set show that the accuracy of sentiment classification is as high as 98%.
Key words: Sentiment classification / Bidirectional gated recurrent unit / Text classification
© The Authors, published by EDP Sciences, 2020
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.