首页    期刊浏览 2024年11月28日 星期四
登录注册

文章基本信息

  • 标题:Comparison of Deep Learning Methods Used to Detect the Similarity Between Two Texts
  • 本地全文:下载
  • 作者:El Mostafa HAMBI ; Faouzia Benabbou
  • 期刊名称:International Journal of Computer Science and Network Security
  • 印刷版ISSN:1738-7906
  • 出版年度:2019
  • 卷号:19
  • 期号:10
  • 页码:26-30
  • 出版社:International Journal of Computer Science and Network Security
  • 摘要:Recently deep learning has proposed several methods used in several domains. Among these domains we found its use in the texts processing, since they have given relevant results at the level of text classification, detection of text similarity and translation detection, that’s why we will use these algorithms in our study. In this paper we will compare the different algorithms used to detect semantics similarity between two given texts. This comparison will give us a global vision to contribute a relevant system that can detect the different types of similarity proposed by a Corpus. In our study we will compare the use of siamese lstm which uses word2vec to have a vector representation of words and siamese lstm which uses doc2vec for the vector representation of sentences to perform the comparison between two texts.
  • 关键词:Deep Learning; Preprocessing;Doc2vev;Word2vec;neural network;Long short-term memory (LSTM);Convolutional neural network (Cnn);Siamese neural network.
国家哲学社会科学文献中心版权所有