Measuring sentence similarity from different aspects

Author

Li, Lin ; Xia Hu ; Hu, Xia ; Wang, Jun ; Zhou, Yi-ming

Author_Institution

Sch. of Comput. Sci. & Eng., Beihang Univ., Beijing, China

Volume

4

fYear

2009

fDate

12-15 July 2009

Firstpage

2244

Lastpage

2249

Abstract

The paper proposes to determine sentence similarities from different aspects. Based on the information people get from a sentence, objects-specified similarity, objects-property similarity, objects-behavior similarity and overall similarity are defined to determine sentence similarities from four aspects. Experiments show that the proposed method makes the sentence similarity comparison more exactly and give out a more reasonable result, which is similar to the people´s comprehension to the meanings of the sentences.

Keywords

computational linguistics; grammars; natural language processing; natural language processing; object-behavior similarity; object-property similarity; object-specified similarity; semantic vector; sentence chunking; sentence similarity measurement; shallow parsing; Computer science; Cybernetics; Data mining; Knowledge representation; Legged locomotion; Machine learning; Speech analysis; Text categorization; Text mining; Time measurement; Chunking; Semantic vector; Sentence similarity;

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Learning and Cybernetics, 2009 International Conference on

Conference_Location

Baoding

Print_ISBN

978-1-4244-3702-3

Electronic_ISBN

978-1-4244-3703-0

Type

conf

DOI

10.1109/ICMLC.2009.5212182

Filename

5212182