DocumentCode
3115092
Title
Contextual Analysis Processing Able to Interpret Coherence of Knowledge Representations Related to Reputation
Author
Itoh, Miho
Author_Institution
Keio Univ., Yokohama, Japan
fYear
2009
fDate
13-15 Dec. 2009
Firstpage
528
Lastpage
535
Abstract
A processing technique of interpretation able to capture coherence of contents of multiple foci among sequential concepts and phenomena, disambiguating contextual knowledge representations, is described in this paper. The proposed system can capture cohesion of expressive but simultaneously complicated sentence structures, utilizing the construction of four novel sentence pattern - any Japanese sentence being classifiable into one of these - which clarify role relations between words related with an absolute expression, of unchangeable meaning, called CEE within the predicate. For instance, having a "big heart", a tolerant mind, and, "pretty girl", are both usually understood as a quality; whereas the expressions ¿big words" and "pretty boy", or effeminate boy, have rather a pejorative connotation. To resolve such contextual ambiguity, the system achieves an accurate contextual analysis, by identifying the overall role relationships between semantic representations. For the determination of the evaluation polarity, in a corpus composed of 2500 customer reviews, the correct answer rate reached 75.0%.
Keywords
knowledge representation; natural language processing; Japanese sentence; contextual ambiguity; contextual analysis processing; contextual knowledge representation; evaluation polarity; pejorative connotation; reputation; sentence pattern; sentence structures; sequential concept; Brightness; Heart; Internet; Knowledge representation; Machine learning; Mood; Natural languages; Object detection; A more realistic natural language application; Coherence of contents of multiple foci; Disambiguating contextual knowledge representations; Representations of unchangeable meaning called CEE; Reputation;
fLanguage
English
Publisher
ieee
Conference_Titel
Machine Learning and Applications, 2009. ICMLA '09. International Conference on
Conference_Location
Miami Beach, FL
Print_ISBN
978-0-7695-3926-3
Type
conf
DOI
10.1109/ICMLA.2009.88
Filename
5381427
Link To Document