DocumentCode
476271
Title
Analysis of cognition commonality using descriptive corpus
Author
Wang, Hsien-chang ; Li, Cheng-chieh ; Yang, Pei-ching
Author_Institution
Dept. of Inf. Manage., Chang Jung Christian Univ., Tainan
Volume
6
fYear
2008
fDate
12-15 July 2008
Firstpage
3178
Lastpage
3182
Abstract
This paper aims to discover the cognition commonality among several people while observing a physical object by analysis of large amount of descriptive about the object. The methodology contains four major tasks: (1) object description corpus collection, (2) linguistic processing of the corpus, (3) analysis of the descriptive sentences, and (4) building the cognition commonality model. The description of an object can be decomposed into several partial structure patterns (PSP) which are the combination of major component keywords plus the corresponding attributes. Perform statistical analysis on the PSP reveal the structural of the cognition commonality about the target object. Taking the wild birds in Taiwan as experiment target, our study had discovered the common structure of how an object is described. The results are useful as the authors are building a bird inquiring system which allows users to query about a specific bird by input the cognized
Keywords
cognition; natural language processing; speech recognition; statistical analysis; cognition commonality analysis; descriptive sentence analysis; linguistic processing; object description corpus collection; partial structure patterns; statistical analysis; Birds; Buildings; Cognition; Cybernetics; Hidden Markov models; Information analysis; Machine learning; Natural languages; Speech recognition; Speech synthesis; Cognition commonality; Major component keyword; Object description; Partial structure pattern;
fLanguage
English
Publisher
ieee
Conference_Titel
Machine Learning and Cybernetics, 2008 International Conference on
Conference_Location
Kunming
Print_ISBN
978-1-4244-2095-7
Electronic_ISBN
978-1-4244-2096-4
Type
conf
DOI
10.1109/ICMLC.2008.4620954
Filename
4620954
Link To Document