收藏切换
Adaptive Pipeline Unsupervised Question Generation Method
收藏切换
Kunze Li, Yu Zhang*
Journal of Computer Research and Development | 2025, 62(4) : 905 - 914
Less
收藏切换
Journal of Computer Research and Development | 2025, 62(4): 905-914
• Artificial Intelligence •
Adaptive Pipeline Unsupervised Question Generation Method
Full
Kunze Li, Yu Zhang*
Affiliations
  • Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology, Harbin 150001
  • born in 2000. Master candidate. Student member of CCF. His main research interests include natural language processing and question generation

    born in 1972. PhD, professor, PhD supervisor. Member of CCF. His main research interests include natural language processing, question answering system, and information retrieval

About Author:

born in 2000. Master candidate. Student member of CCF. His main research interests include natural language processing and question generation

born in 1972. PhD, professor, PhD supervisor. Member of CCF. His main research interests include natural language processing, question answering system, and information retrieval

Published: 2025-04-01 doi: 10.7544/issn1000-1239.202330857
Outline
收藏切换

In traditional question-answering tasks, models generally require extensive data for training, which entails considerable time and manpower costs for data annotation. Unsupervised question generation represents an effective solution to address the scarcity of training data in question-answering tasks. However, the questions generated using this approach currently suffer from issues such as being difficult to answer, lacking variety, and having unclear semantics. To address these issues, we propose an adaptive multi-module pipeline model named ADVICE, with modules improving existing methods in answerability, question diversity and grammatical correctness. Within the question answerability module, we employ coreference resolution and named entity recognition techniques to improve the answerability of questions. For question diversity, we design specific rules for various question types to enhance the diversity of question and answer types. In the grammatical correctness module, a grammar error correction model targeted at questions is trained based on T5 model, and a filtering module is designed to refine the generated question-answer data. Finally, a classifier is trained to automatically select the necessary modules. Experiments demonstrate that the improved question generation method enhances the performance of downstream question-answering models on the SQuAD dataset, with the EM (exact match) score increasing by an average of 2.9% and the F1 score by an average of 4.4%.

unsupervised learning  /  question generation  /  pre-trained model  /  deep learning  /  natural language processing
李昆泽, 张宇. 自适应的流水线式无监督问题生成方法. 计算机研究与发展, 2025 , 62 (4) : 905 -914 . DOI: 10.7544/issn1000-1239.202330857
Kunze Li, Yu Zhang. Adaptive Pipeline Unsupervised Question Generation Method[J]. Journal of Computer Research and Development, 2025 , 62 (4) : 905 -914 . DOI: 10.7544/issn1000-1239.202330857
Year 2025 volume 62 Issue 4
139
68
Cite this Article
BibTeX
Article Info
doi: 10.7544/issn1000-1239.202330857
  • Receive Date:2023-10-31
  • Online Date:2026-11-10
  • Published:2025-04-01
Article Data
Affiliations
History
  • Received:2023-10-31
  • Revised:2024-07-08
  • Accepted:2024-08-09
Affiliations
    Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology, Harbin 150001
References
Share
https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202330857
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT