In accordance with regulations and requirements, the editorial department's website domain has been changed to arocmag.cn. The original domain (arocmag.com) will be discontinued after Dec. 31st, 2024.
Algorithm Research & Explore
|
421-425

Two-stage clarification question generation method based on Prompt

Wang Peibing
Zhang Ning
Zhang Chun
School of Computer & Information Technology, Beijing Jiaotong University, Beijing 100044, China

Abstract

In natural language-oriented systems, generating clarification questions to ask users when their input is ambiguous can help the system better understand the user's requirements. Although Prompt-based approaches can better exploit the latent knowledge of pre-trained language models, they often require hand-designed templates, constraining their diversity in generating clarification questions. To address this limitation, this paper proposed the two-stage clarification question generation(TSCQG) method. Firstly, in the dynamic Prompt template generation stage, the TSCQG method used the ambiguous context and the pre-trained language models to generate Prompt templates. Then, in the missing information generation stage, it combined the Prompt templates and relevant external knowledge and capitalized on the generative potential of the pre-trained model to generate relevant missing information. Experimental results demonstrate that the BLEU value and ROUGE-L value of the multi-round dialogue situation on the CLAQUA dataset reach 58.31 and 84.33, and the BLEU value and ROUGE-L value on the ClariQ-FKw dataset reach 31.18 and 58.86, respectively. The experimental results validate the effectiveness of the TSCQG method in clarification question generation tasks.

Foundation Support

国家重点研发计划资助项目(2019YFB1405202)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2023.07.0271
Publish at: Application Research of Computers Printed Article, Vol. 41, 2024 No. 2
Section: Algorithm Research & Explore
Pages: 421-425
Serial Number: 1001-3695(2024)02-015-0421-05

Publish History

[2023-09-01] Accepted Paper
[2024-02-05] Printed Article

Cite This Article

王培冰, 张宁, 张春. 基于Prompt的两阶段澄清问题生成方法 [J]. 计算机应用研究, 2024, 41 (2): 421-425. (Wang Peibing, Zhang Ning, Zhang Chun. Two-stage clarification question generation method based on Prompt [J]. Application Research of Computers, 2024, 41 (2): 421-425. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.


Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2022 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)