Knowledge Network Node

Answer selection model based on bert-lstmChinese Full Text

ZHU Jian;RAO Hong;LI Shan;Information Engineering School, Nanchang University;

Abstract: At present, the answer selection algorithms are mainly based on word2 vec/glove for word representation firstly, and use RNN or CNN to extract text semantic features.Nonetheless, word2 vec/glove cannot solve the problem of polysemy, and RNN and CNN have limitations in extracting global text features.In view of the above shortcomings, this paper proposes an answer selection algorithm, termed as BERT-STM,based on the BERT pre-training model.Firstly, the semantic feature representation of the quest... More
  • DOI:

    10.13764/j.cnki.ncdl.2021.01.014

  • Series:

    (A) Mathematics/ Physics/ Mechanics/ Astronomy; (I) Electronic Technology & Information Science

  • Subject:

    Computer Software and Application of Computer

  • Classification Code:

    TP391.1

  • Mobile Reading
    Read on your phone instantly
    Step 1

    Scan QR Codes

    "Mobile CNKI-CNKI Express" App

    Step 2

    Open“CNKI Express”

    and click the scan icon in the upper left corner of the homepage.

    Step 3

    Scan QR Codes

    Read this article on your phone.

  • HTML
  • Read online
  • CAJ Download
  • PDF Download

Download the mobile appuse the app to scan this coderead the article.

Tips: Please download CAJViewer to view CAJ format full text.

Download: 306 Page: 85-90 Pagecount: 6 Size: 852K

Related Literature
  • Similar Article
  • Reader Recommendation
  • Associated Author