Title :
A concept-based knowledge representation model for semantic entailment inference
Author :
Zhao Meijing ; Ni Wancheng ; Zhang Haidong ; Yang Yiping
Author_Institution :
Dept. of CASIA-HHT Joint Lab. of Smart Educ., Inst. of Autom., Beijing, China
Abstract :
Semantic entailment is a fundamental problem in natural language understanding field which has a large number of applications. Knowledge acquisition and knowledge representation are crucial parts in semantic inference strategies. This paper presents a principled approach to semantic entailment problem that builds on a concept-based knowledge representation model (CKR). This model formally defines the concept as a triple (attribute, relation and behavior) and the knowledge of a concept can be illustrated by the triple. We propose a semantic inference strategy that against identify text segments which with dissimilar surface form but share a common meaning. The inference strategy avoids syntactic analysis steps. A preliminary evaluation on the PASCAL text collection is presented. Experimental results show that our concept-based inference strategy is effective and has strong development potential.
Keywords :
inference mechanisms; knowledge acquisition; knowledge representation; natural language processing; text analysis; CKR; PASCAL text collection; concept-based knowledge representation model; knowledge acquisition; natural language understanding field; semantic entailment inference strategy; syntactic analysis steps; text segment identification; Abstracts; Data preprocessing; Decision support systems; Knowledge representation; Liquids; Ocean temperature; Semantics; CKR; Concept; Knowledge representation; Semantic entailment; Semantic inference;
Conference_Titel :
Control Conference (CCC), 2014 33rd Chinese
Conference_Location :
Nanjing
DOI :
10.1109/ChiCC.2014.6896678