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

A.A. Litvin, V.Yu. Velychko, V.V. Kaverynskyi

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.

Prombles in programming 2022; 3-4: 196-207


Keywords


ontology; Neo4j; Cypher; text analysis; automatic ontology generation; semantic analysis; natural language text synthesis; natural language processing; natural language understanding

Full Text:

PDF

References


A. Litvin, V. Velychko, & V. Kaverinsky (2022) A new approach to automatic ontology creation from untagged text on natural language of inflective type. International conference on software engineering “Soft Engine 2022”. Kyiv, NAU. Available from: http://pp.isofts.kiev.ua/ ojs1/ article/view/145 [Accessed 6/06/2017].

A. Litvin, V. Velychko, & V. Kaverinsky (2021) Development of natural language dialogue software systems. Information Theories and Applications. 28. p. 233 – 270.

Quamar Abdul, Fatma Ozcan, Dorian Miller , Robert J. Moore , Rebecca Niehus & Jeffrey Kreulen Conversational BI: An Ontology-Driven Conversation System for Business Intelligence Applications. Proceedings of the VLDB Endowment. 13. p. 3369 – 3381.

Abdul Quamar, Chuan Lei, Dorian Miller , Fatma Özcan1, Jeffrey Kreulen, Robert J. Moore, Vasilis Efthymiou (2020) An Ontology-Based Conversation System for Knowledge Bases Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data. p. 361 – 375. DOI:10.1145/3318464.3386139.

P. Ochieng PAROT: Translating natural language to SPARQL. (2020) Expert Systems with Applications. 5. p. 1–16.

D. Damljanovic, M. Agatonovic & H. Cunningham (2011) FREyA: an interactive way of querying linked data using natural language. The

Semantic Web: ESWC 2011 Workshops. p. 125–138.

GIT-hub: FREyA documentation [Online] Available from: https://github.com/nmvijay/freya

S. Shaik, P. Kanakam, S.M. Hussain & D. Suryanarayana (2016) Transforming natural language query to SPARQL for semantic informa- tion retrieval. International Journal of Engineering Trends and Technology. 7. p. 347–350.

Duygu Altinok (2018) An Ontology-Based Dialogue Management System for Banking and Finance Dialogue Systems. 1st Financial Narrative Processing Workshop. Japan, Miyazaki. DOI: https://doi.org/10.48550/arXiv.1804.04838

H. Jung, W. Kim (2020) Automated conversion from natural language query to SPARQL query. Journal of Intelligent Information Systems. 55. p. 501–520.

A. Goel (2015) Neo4J Cookbook. Birmingham: Pact Publishing Ltd.

C. Sun A. (2018) Natural Language Interface for Querying Graph Databases: master’s thesis master in computer science and engineering. USA: Massachusetts Institute of Technology.

GIT-hub Convert English sentences to Cypher queries documentation [Online] Available from: https://github.com/gsssrao/english2cypher

A. Litvin, V. Velychko, & V. Kaverinsky (2020) Synthesis of chat-bot responses in the inflecting natural language based on the results of queries to ontology and analysis of the chat previous phrase. Information Theories and Application. 27. p. 152 – 199.


Refbacks

  • There are currently no refbacks.