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

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

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”, &#x2...

Full description

Bibliographic Details
Main Authors: Li-Yuan Hsu, Chia-Hao Kao, I-Sheng Jheng, Hung-Hsuan Chen
Format: Article
Language:English
Published: IEEE 2021-01-01
Series:IEEE Access
Subjects:
Bidirectional LSTM
hierarchical LSTM
document understanding
specialty search engine
Online Access:https://ieeexplore.ieee.org/document/9504549/
Description
Summary: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.
ISSN:2169-3536

Similar Items