Toward Building an Academic Search Engine Understanding the Purposes of the Matched Sentences in an Abstract

IEEE Access

Li-Yuan Hsu¹  Hung-Hsuan Chen²  I-Sheng Jheng³  Chia-Hao Kao⁴ 

[1] Department of Computer Science and Engineering, Texas A&x0026;Department of Computer Science and Information Engineering, National Central University, Taoyuan, Taiwan;Department of Computer Science, National Yang Ming Chiao Tung University, Hsinchu, Taiwan;M University, College Station, TX, USA;

关键词: Bidirectional LSTM;    hierarchical LSTM;    document understanding;    specialty search engine;   

DOI  :  10.1109/ACCESS.2021.3102005

来源: DOAJ

【 摘 要 】

This paper introduces an automatic approach to understand the purposes of each sentence in the abstract of an academic document. Specifically, computers can label each sentence in the abstract as being related to one or several of six aspects – “BACKGROUND”, “OBJECTIVES”, “METHODS”, “RESULTS”, “CONCLUSIONS”, and “OTHERS”. Experimental results obtained on a real dataset show that the labeling methodology outperforms baseline methods. We also build a prototype academic search engine to demonstrate the use of this new design. Users may search for articles containing keywords related to any of these six aspects to better meet their search goals.

【 授权许可】

Unknown