On the basis of summarizing the concept filtering methods in the current Ontology learning, a method of domain concept filtering in the semantic level based on combination of word embedding and conventional statistics was presented, which can identify low-frequency words well, and as far as possible to ensure universality. Through experimental contrast, the proposed approach was proved to have a higher accuracy rate than the ways based on statistics.
Paper
Full text
Domain Concept Filtering Method Based on Word Embedding and Statistics
Semantic Scholar · Computer Science · 2014
Abstract
On the basis of summarizing the concept filtering methods in the current Ontology learning, a method of domain concept filtering in the semantic level based on combination of word embedding and conventional statistics was presented, which can identify low-frequency words well, and as far as possible to ensure universality. Through experimental contrast, the proposed approach was proved to have a higher accuracy rate than the ways based on statistics.