Reading comprehension system based on knowledge structures

Author

Chen, Yue ; Wang, Zhifei ; Zhu, Jian

Author_Institution

Sch. of Comput., Beijing Inst. of Technol., Beijing, China

Volume

4

fYear

2010

fDate

16-18 April 2010

Abstract

This paper describes initial work on an automated reading comprehension system that accepts arbitrary text input and generates answers to the questions about the text. An approach to implement reading comprehension system is proposed in this paper. Firstly, the article will be decomposed according to paragraph, sentence and phrase. Every sentence will be compared with the knowledge node, and then append the knowledge representation to the knowledge model. Finally, the answer is generated for the questions. With the experimental corpus the precision of knowledge matching is 65.0%, and precision of question answering is 81.5% with the system knowledge model.

Keywords

knowledge representation; natural language processing; arbitrary text input; article; knowledge structures; natural language processing; reading comprehension system; Computer science; Data mining; Information analysis; Information retrieval; Knowledge representation; Mathematics; Natural language processing; Natural languages; Robustness; Vocabulary; Natural Language Processing; knowledge representation; knowledge structure; reading comprehension;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Engineering and Technology (ICCET), 2010 2nd International Conference on

Conference_Location

Chengdu

Print_ISBN

978-1-4244-6347-3

Type

conf

DOI

10.1109/ICCET.2010.5486356

Filename

5486356