English Sentence Evaluation Method using Text Clustering and Semantic Ontology

Aiming at the problem that the identification precision in intonation evaluation and analysis of English sentences is not high, this paper proposes a method of English sentences on the basis of ontology graph clustering evaluation. First, we study the ontology-graph evaluation model of English sentences, conduct objective evaluation to English sentences based on the fundamental framework of KL Seeker system, and take the rhythms and stresses of sentences as major indexes (each index is expressed by different phonetic features during evaluation). Second, we evaluate and analyze intonations of English sentences using clustering ontology-graph classification model. Experimental results show that the proposed method, as compared with contrast algorithm, is closer to the teachers’ evaluation results, which proves its advantage in evaluation precision.