模式识别与人工智能
Thursday, Apr. 3, 2025 Home      About Journal      Editorial Board      Instructions      Ethics Statement      Contact Us                   中文
Pattern Recognition and Artificial Intelligence  2022, Vol. 35 Issue (5): 401-411    DOI: 10.16451/j.cnki.issn1003-6059.202205002
Papers and Reports Current Issue| Next Issue| Archive| Adv Search |
Text Summary Generation ModelBased on Sentence Fusion and Self-Supervised Training
ZOU Ao1, HAO Wenning1, JIN Dawei1, CHEN Gang1
1. College of Command and Control Engineering, Army Engineering University of PLA, Nanjing 210007

Download: PDF (916 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  To improve the capability of sentence fusion of deep neural network text generation technique, a text summary generation model based on sentence fusion and self-supervised training is proposed. Before the model training, the training data are firstly pre-processed according to the concept of points of correspondence in the theory of sentence fusion, and thus the data can meet the needs of model training. The training of the proposed model falls into two parts. In the first stage, according to the distribution of the sentence fusion phenomenon in the dataset, the training task of the permutation language model is designed with the points of correspondence as the minimum semantic unit to enhance the ability to capture the information of the fused sentence context. In the second stage, an attention masking strategy based on the fusion information is utilized to control the information intake of the model during the text generation process to enhance the fusion ability in the text generation stage. Experiments on the open dataset show that the proposed model is superior in several evaluation metrics, including those based on statistics, deep semantics and sentence fusion ratio.
Key wordsAutomatic Text Summarization      Sentence Fusion      Pre-trained Language Model      Deep Neural Network      Self-Supervised Training     
Received: 25 February 2022     
ZTFLH: TP391  
Fund:National Natural Science Foundation of China(No.61806221)
Corresponding Authors: HAO Wenning, Ph.D., professor. His research interests include data mining and machine learning.   
About author:: ZOU Ao, Ph.D. candidate. His research interests include natural language processing and deep learning.
JIN Dawei, master, associate professor. His research interests include big data and text data mining.
CHEN Gang, master, professor. His research interests include data simulation and deep learning.
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
ZOU Ao
HAO Wenning
JIN Dawei
CHEN Gang
Cite this article:   
ZOU Ao,HAO Wenning,JIN Dawei等. Text Summary Generation ModelBased on Sentence Fusion and Self-Supervised Training[J]. Pattern Recognition and Artificial Intelligence, 2022, 35(5): 401-411.
URL:  
http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.202205002      OR     http://manu46.magtech.com.cn/Jweb_prai/EN/Y2022/V35/I5/401
Copyright © 2010 Editorial Office of Pattern Recognition and Artificial Intelligence
Address: No.350 Shushanhu Road, Hefei, Anhui Province, P.R. China Tel: 0551-65591176 Fax:0551-65591176 Email: bjb@iim.ac.cn
Supported by Beijing Magtech  Email:support@magtech.com.cn