Dependency relationship-based teaching domain ontology automatic generation method and apparatus

Abstract

The invention discloses a dependency relationship-based teaching domain ontology automatic generation method. The method comprises the steps of firstly extracting and automatically generating a domainterm list from teaching materials through TF_IDF weights, and converting domain terms in the domain term list into concepts in a teaching domain ontology, thereby generating an initial teaching domain ontology only with a single-layer structure; secondly according to characteristics of various teaching domain relationships, defining dependency relationship-based sentence templates for describingan ontology relationship, thereby forming a sentence template library for describing the ontology relationship; and finally performing template matching, ontology relationship information extraction and ontology relationship automatic generation according to the steps. Apparatuses involved in the method include the domain term list, the sentence template library, a sentence preprocessing module, atemplate inference engine and an ontology relationship generator. The method has the advantages that the templates are not influenced by physical positions of sentence structures; the expandability is high; the teaching domain ontology automatic generation accuracy is high; and the method can be widely applied to automatic construction of the teaching domain ontology in an intelligent teaching system of all disciplines.

Description

technical field [0001] The present invention relates to natural language processing, knowledge management and information extraction in the field of artificial intelligence, and specifically to a method and device for automatically generating ontology in the teaching field based on dependency relationships. The method and device use computers as tools and textbook text corpus as processing objects. Realize the automatic generation of teaching domain ontology, which can be widely used in the automatic construction of teaching domain ontology in teaching expert system, teaching question answering system and intelligent teaching system of various disciplines. Background technique [0002] Ontology originated from philosophy. It is a standardized and formalized description of objectively existing things. With the development of information technology, ontology was introduced into the information field in the 1980s, which led to the emergence of Semantic Web. Ontology has the c...

AI Technical Summary

Problems solved by technology

Among them, the sentence template method uses pre-designed templates or patterns to classify sentences and extract relational information, so the accuracy is high, but limited by the size of the template, its adaptability and versatility are poor; while the machine learning method , through the method of statistical or semantic analysis to classify sentences and extract relational information, it does not need to design templates in advance, so it has strong adaptability but low precision

Traditional sentence templates and association rules methods generally use keywords or phrases as features, such as the method of "Analysis and Knowledge Extraction of Primary School Application Questions and Sentences Based on Conceptual Hierarchical Networks" proposed by Pan Li and Feng Su. The disadvantage is that the template is easily affected by the physical location of the characteristic words, so the versatility is poor, and a large-scale template library needs to be established

Although Gu Linglan and Sun Suyun proposed the "Semantic Dependence-Based Chinese Ontology Non-categorical Relation Extraction Method", which can overcome the influence of sentence features on physical locations, but they did not establish accurate sentence templates through semantic dependencies, but through Semantic analysis finds ontology relationships and related information, but the accuracy of relationship extraction is not high, only about 60% correct

In addition, this method can only extract the non-categorical relationship of the ontology, but cannot extract the classification relationship that constitutes the concept hierarchy of the ontology, and needs the support of the concept level of the domain ontology, so this method cannot fully realize the automatic generation of the domain ontology

Images