Data Analysis and Knowledge Discovery  2022, Vol. 6 Issue (2/3): 105-116    DOI: 10.11925/infotech.2096-3467.2021.0912
 Current Issue | Archive | Adv Search |
A Multi-Task Text Classification Model Based on Label Embedding of Attention Mechanism
Xu Yuemei1(),Fan Zuwei2,3,Cao Han1
1School of Information Science and Technology, Beijing Foreign Studies University, Beijing 100089, China
2Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100093, China
3School of Cyber Security, University of Chinese Academy of Sciences, Beijing 100049, China
 Download: PDF (1842 KB)   HTML ( 18 )  Export: BibTeX | EndNote (RIS)
Abstract

[Objective] This paper tries to adjust text classification algorithm according to task-specific features, aiming to improve the accuracy of text classification for different tasks. [Methods] We proposed a text classification algorithm based on label attention mechanism. Through label embedding learning of both word vector and the TF-IDF classification matrix, we extracted the task-specific features by assigning different weights to the words, which improves the effectiveness of the attention mechanism. [Results] The accuracy of the proposed method increased by 3.78%, 5.43%, and 11.78% in prediction compared with the existing LSTMAtt, LEAM and SelfAtt methods. [Limitations] We did not study the impacts of different vector models on the performance of text classification.[Conclusions] This paper presents an effective method to improve and optimize the multi-task text classification algorithm.

Received: 05 August 2021      Published: 14 April 2022
 ZTFLH: TP393
Fund:Fundamental Research Funds for the Central Universities(2022JJ006)
Corresponding Authors: Xu Yuemei,ORCID： 0000-0002-0223-7146     E-mail: xuyuemei@bfsu.edu.cn
 Procedure of Text Classification Based on LabelAtt Model Experiment Procedure Experiment Datasets Parameter Settings of LabelAtt Model Confusion Matrix of Classification Category $i$ Accuracy on TREC, CR, and SST-1 Dataset LabelAtt’s Text Classification Scatter Diagram on TREC Dataset When Epoch=1, 5, 20, 25 LSTMAtt’s Text Classification Scatter Diagram on TREC Dataset When Epoch=1, 5, 20, 25 Accuracy of LabelAtt and LSTMAtt on TREC Dataset Attention Weights of LSTMAtt and LabelAtt on TREC Dataset Attention Weights of LSTMAtt and LabelAtt on CR Dataset