About | Contact Us | Register | Login
ProceedingsSeriesJournalsSearchEAI
Communications and Networking. 16th EAI International Conference, ChinaCom 2021, Virtual Event, November 21-22, 2021, Proceedings

Research Article

Text Error Correction Method in the Construction Industry Based on Transfer Learning

Download(Requires a free EAI acccount)
7 downloads
Cite
BibTeX Plain Text
  • @INPROCEEDINGS{10.1007/978-3-030-99200-2_22,
        author={Zhenguo Hou and Weitao Yang and Haiying He and Peicong Zhang and Ziyu Wang and Xiaosheng Ji},
        title={Text Error Correction Method in the Construction Industry Based on Transfer Learning},
        proceedings={Communications and Networking. 16th EAI International Conference, ChinaCom 2021, Virtual Event, November 21-22, 2021, Proceedings},
        proceedings_a={CHINACOM},
        year={2022},
        month={4},
        keywords={Text error correction Transfer learning BERT model Multi-domain text},
        doi={10.1007/978-3-030-99200-2_22}
    }
    
  • Zhenguo Hou
    Weitao Yang
    Haiying He
    Peicong Zhang
    Ziyu Wang
    Xiaosheng Ji
    Year: 2022
    Text Error Correction Method in the Construction Industry Based on Transfer Learning
    CHINACOM
    Springer
    DOI: 10.1007/978-3-030-99200-2_22
Zhenguo Hou1,*, Weitao Yang1, Haiying He1, Peicong Zhang1, Ziyu Wang2, Xiaosheng Ji3
  • 1: China Construction Seventh Engineering Bureau Co., Ltd., Zhengzhou
  • 2: Hohai University Industrial Technology Research Institute, Changzhou
  • 3: College of IoT Engineering, Hohai University, Changzhou
*Contact email: houzhenguo@cscec.com

Abstract

Text error correction is of great value in the review of texts in the construction industry. For construction industry texts, which are compound texts with multi-domain proper nouns, the lack of labeled data leads to poor error correction algorithms based on deep learning. For this reason, this paper proposes a text error correction method in the construction industry based on transfer learning. Based on the pre-trained BERT model, we transfer some parameters to the target error correction model after unsupervised training by unlabeled related field dataset, and then retrain the model through the training samples of the construction document corpus dataset to obtain better error correction effects. Meanwhile, we dynamically adjust the pre-training task in transfer learning to improve the performance of the word order correction task. Experimental results show that our proposed model has higher precision rate, recall rate and lower false positive rate in the error correction task than other models.

Keywords
Text error correction Transfer learning BERT model Multi-domain text
Published
2022-04-05
Appears in
SpringerLink
http://dx.doi.org/10.1007/978-3-030-99200-2_22
Copyright © 2021–2025 ICST
EBSCOProQuestDBLPDOAJPortico
EAI Logo

About EAI

  • Who We Are
  • Leadership
  • Research Areas
  • Partners
  • Media Center

Community

  • Membership
  • Conference
  • Recognition
  • Sponsor Us

Publish with EAI

  • Publishing
  • Journals
  • Proceedings
  • Books
  • EUDL