Advertisement
Published in:
08-02-2018
A Study on Characteristics of MSAV Based on SAL-F Algorithm
Published in: Wireless Personal Communications | Issue 2/2018
Log inActivate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
Abstract
The traditional method of lexical interpretation is to use a few words to explain some other words. Its lexical semantic information cannot be applied to natural language processing oriented towards physical contexts, on the basis of which the paper proposes a lexical semantic representation model based on graphic feature vectors and its learning algorithm Sal-F. The algorithm applies cross-situational learning to the alignment of word-graph features, establishes visual semantic model of words (Lsm-G) on the basis of the feature selection results and constructs semantic dictionary based on graphic features. According to evaluation methods such as machine translation, the algorithm achieves a word average accuracy of 70% and the highest sentence accuracy of 16%.