A document-level summary extraction model based on BigBird

JiaQi Hao

doi:10.1117/12.2646928

7 September 2022 A document-level summary extraction model based on BigBird

JiaQi Hao

Proceedings Volume 12329, Third International Conference on Artificial Intelligence and Electromechanical Automation (AIEA 2022); 1232913 (2022) https://doi.org/10.1117/12.2646928
Event: Third International Conference on Artificial Intelligence and Electromechanical Automation (AIEA 2022), 2022, Changsha, China

Abstract

Traditional single-model document-level summary extraction methods lack a multi-level representation of features and cannot extract feature information from documents well. To this end, the text uses the BigBird model and Transformer model to extract the sentence features and document features of the document respectively, to obtain a more comprehensive multi-level feature representation of the document and extract a more accurate document summary. In addition, the BigBird model for the sentence encoding layer, which increases the length of the input text sequence through a sparsity attention mechanism, solves the problem that traditional single-model document-level summary extraction methods cannot focus on more comprehensive contextual information and reduces the model time and space complexity. Comparative experiments are conducted on a generic dataset, and the experimental results demonstrate the effectiveness of the proposed method.

Citation Download Citation

JiaQi Hao "A document-level summary extraction model based on BigBird", Proc. SPIE 12329, Third International Conference on Artificial Intelligence and Electromechanical Automation (AIEA 2022), 1232913 (7 September 2022); https://doi.org/10.1117/12.2646928

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available