A dialogue system based on ontology automatically built through a natural language text analysis

Abstract

An integrated approach is created to the development of natural-language dialogue systems driven by an ontological graph database. Ontology here has a defined regular structure that contains typed semantic relationships between concepts, as well as related contexts, which may also have a multilevel structure and additional typing. The ontology is created automatically due to the semantic analysis of a natural language using a specially developed original software, which is set up to work with inflected languages, in particular Ukrainian. The ontology description is serialized in OWL format. To work as part of the dialog system, the ontology is transferred to the graph database Neo4j. The Cypher language is used for formal queries. The original phrases of the user are subject to a special method of semantic analysis, which determines the type of formal query to the database. The essence of the analysis is that the text of the user phrase goes through a series of checks. Based on their results, a set of basic templates for formal requests is determined, as well as additional constructions that are attached to the basic template. Some of the checks may also return the notion of substitution to certain specified positions of the formal query. Formal queries can return both contexts and lists of ontology concepts. In addition to concepts, queries can also return information about specific semantic predicates that connect them, which simplifies the synthesis of natural language responses. The synthesis of answers is based on special templates, the choice of which is directly related to the corresponding template of the formal query.

Ontology Related Natural Text Semantic Analysis Approaches

“…The automated creation of ontology and graph databases based on natural language text analysis finds widespread applications in various fields For instance, in medicine, this approach can be used to create ontologies that help account for different medical terms and their interconnections In the field of bioinformatics, automated ontology construction assists in integrating data about genes, proteins, and reactions into a unified model This approach is also applied in e-commerce for analyzing customer behaviour and recommendation systems In the financial sector, graph databases are utilized for detecting financial fraud and risk analysis Automated ontology creation and graph databases based on natural language text analysis represent a significant research direction in computer science, cybernetics, and knowledge engineering The use of Natural Language Processing (NLP) technologies and graph databases allows the automation of the knowledge creation and processing process, which is valuable across various domains The research findings in this direction are already being applied in different industries, and this approach has the potential for further development and refinement In certain cases, a text (or a set of texts) exhibits a regularly predefined structure That is, in specific locations, it is guaranteed or with a high probability to contain information of a certain type presented in a defined format Thus, it is possible to devise a software instruction by which a machine can construct an ontology-based database from a set of similar texts Examples of such input material from our practical experience include, for instance, a collection of letters [23] or a set of PDF files of EBSCO medical and medical rehabilitation articles [24] Let us regard an example of the ontology structure for letters: Place -locations (usually cities) from which the letters were sent; Year -years for which the letters were sent TextLink -links to the full texts of the letters The properties within the ontology are as follows:…”