A concept-based knowledge representation model for semantic entailment inference

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 probl...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhao Meijing, Ni Wancheng, Zhang Haidong, Yang Yiping
Format: Conference Proceeding
Language:English
Subjects:
Abstracts
CKR
Concept
Data preprocessing
Decision support systems
Knowledge representation
Liquids
Ocean temperature
Semantic entailment
Semantic inference
Semantics
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2161-2927
DOI:10.1109/ChiCC.2014.6896678