Question-Answer systems are now very popular and crucial to support human in automatically responding frequent questions in manyfields.However,these systems depend on learning methods and training data.Therefore,it is ...Question-Answer systems are now very popular and crucial to support human in automatically responding frequent questions in manyfields.However,these systems depend on learning methods and training data.Therefore,it is necessary to prepare such a good dataset,but it is not an easy job.An ontol-ogy-based domain knowledge base is able to help to reason semantic information and make effective answers given user questions.This study proposes a novel chatbot model involving ontology to generate efficient responses automatically.A case study of admissions advising at the International University–VNU HCMC is taken into account in the proposed chatbot.A domain ontology is designed and built based on the domain knowledge of university admissions using Protégé.The Web user interface of the proposed chatbot system is developed as a prototype using NetBeans.It includes a search engine reasoning the ontology and generat-ing answers to users’questions.Two experiments are carried out to test how the system reacts to different questions.Thefirst experiment examines questions made from some templates,and the second one examines normal questions taken from frequent questions.Experimental results have shown that the ontology-based chatbot can release meaningful and long answers.The results are analysed to prove the proposed chatbot is usable and promising.展开更多
The paper considers the problem of semantic processing of web documents by designing an approach, which combines extracted semantic document model and domain- related knowledge base. The knowledge base is populated wi...The paper considers the problem of semantic processing of web documents by designing an approach, which combines extracted semantic document model and domain- related knowledge base. The knowledge base is populated with learnt classification rules categorizing documents into topics. Classification provides for the reduction of the dimensio0ality of the document feature space. The semantic model of retrieved web documents is semantically labeled by querying domain ontology and processed with content-based classification method. The model obtained is mapped to the existing knowledge base by implementing inference algorithm. It enables models of the same semantic type to be recognized and integrated into the knowledge base. The approach provides for the domain knowledge integration and assists the extraction and modeling web documents semantics. Implementation results of the proposed approach are presented.展开更多
基金funded by International University,VNU-HCM under Grant Number T2020-03-IT.
文摘Question-Answer systems are now very popular and crucial to support human in automatically responding frequent questions in manyfields.However,these systems depend on learning methods and training data.Therefore,it is necessary to prepare such a good dataset,but it is not an easy job.An ontol-ogy-based domain knowledge base is able to help to reason semantic information and make effective answers given user questions.This study proposes a novel chatbot model involving ontology to generate efficient responses automatically.A case study of admissions advising at the International University–VNU HCMC is taken into account in the proposed chatbot.A domain ontology is designed and built based on the domain knowledge of university admissions using Protégé.The Web user interface of the proposed chatbot system is developed as a prototype using NetBeans.It includes a search engine reasoning the ontology and generat-ing answers to users’questions.Two experiments are carried out to test how the system reacts to different questions.Thefirst experiment examines questions made from some templates,and the second one examines normal questions taken from frequent questions.Experimental results have shown that the ontology-based chatbot can release meaningful and long answers.The results are analysed to prove the proposed chatbot is usable and promising.
文摘The paper considers the problem of semantic processing of web documents by designing an approach, which combines extracted semantic document model and domain- related knowledge base. The knowledge base is populated with learnt classification rules categorizing documents into topics. Classification provides for the reduction of the dimensio0ality of the document feature space. The semantic model of retrieved web documents is semantically labeled by querying domain ontology and processed with content-based classification method. The model obtained is mapped to the existing knowledge base by implementing inference algorithm. It enables models of the same semantic type to be recognized and integrated into the knowledge base. The approach provides for the domain knowledge integration and assists the extraction and modeling web documents semantics. Implementation results of the proposed approach are presented.
