Short Text Classification Based on Explicit and Implicit Multiscale Weighted Semantic Information

IF 2.2 3区综合性期刊 Q2 MULTIDISCIPLINARY SCIENCES

Symmetry-Basel Pub Date : 2023-11-01 DOI:10.3390/sym15112008

Jun Gong, Juling Zhang, Wenqiang Guo, Zhilong Ma, Xiaoyi Lv

引用次数: 0

Abstract

Considering the poor effect of short text classification due to insufficient semantic information mining in the current short text matching methods, a new short text classification method is proposed based on explicit and implicit multiscale weighting semantic information interaction. First, the explicit and implicit representations of short text are obtained by a word vector model (word2vec), convolutional neural networks (CNNs), and long short-term memory (LSTM). Then, a multiscale convolutional neural network obtains the explicit and implicit multiscale weighting semantics information of short text. Finally, the multiscale weighting semantics is fused for more accurate short text classification. The experimental results show that this method is superior to the existing classical short text classification algorithms and two advanced short text classification models on the five short text classification datasets of MR, Subj, TREC, SST1 and SST2 with accuracies of 85.7%, 96.9%, 98.1%, 53.4% and 91.8%, respectively.

查看原文本刊更多论文

基于显式和隐式多尺度加权语义信息的短文本分类

针对当前短文本匹配方法中语义信息挖掘不足导致短文本分类效果不佳的问题，提出了一种基于显式和隐式多尺度加权语义信息交互的短文本分类新方法。首先，通过词向量模型(word2vec)、卷积神经网络(cnn)和长短期记忆(LSTM)获得短文本的显式和隐式表示。然后，利用多尺度卷积神经网络获得短文本的显式和隐式多尺度加权语义信息。最后，融合多尺度加权语义，实现更准确的短文本分类。实验结果表明，该方法在MR、Subj、TREC、SST1和SST2 5个短文本分类数据集上的准确率分别为85.7%、96.9%、98.1%、53.4%和91.8%，优于现有的经典短文本分类算法和两种高级短文本分类模型。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Symmetry-Basel MULTIDISCIPLINARY SCIENCES-

CiteScore

5.40

自引率

11.10%

发文量

2276

审稿时长

14.88 days

期刊介绍： Symmetry (ISSN 2073-8994), an international and interdisciplinary scientific journal, publishes reviews, regular research papers and short notes. Our aim is to encourage scientists to publish their experimental and theoretical research in as much detail as possible. There is no restriction on the length of the papers. Full experimental and/or methodical details must be provided, so that results can be reproduced.