Extract science term from web for sms-based learning
Tran, Phuong Nam.
Date of Issue2009
School of Electrical and Electronic Engineering
This report describes a system, from over view to detail, that allows user to extract scientific terms from the Internet for SMS base learning. Its name is tSearch – The Term Definition Searcher. The system receives user’s input for a scientific term, automatically searches for its definitions on the Internet, and summarizes the definitions into one or several sentences. The definitions are short enough (less than 160 characters), making it possible to be sent to the user through SMS. Several text summarization algorithms have been implemented to extract short and concise definitions from long web pages about the scientific terms. These algorithms play a vital role in the system, as the effectiveness of the system depends largely on the speed and correctness of the algorithms, which in turn depends on quality of the output summary. In this project, most of time was spent on researching, implementing, and testing those algorithms. Some standard evaluations of text summarization systems were also performed to evaluate the performances of the algorithms.
Final Year Project (FYP)
Nanyang Technological University