Methods of organizing question-answering systems
G.V. Dorokhina, A.G. Polous
Upload the full text
Abstract. Today the issue of human-machine interaction via natural language text, including the use of question answering systems, is relevant. The purpose of the work is to analyze the methods of developing question answering systems. It was achieved by considering the types of questions and types of question answering systems, describing the methods of building question answering systems. Embedding question answering systems into digital platforms will allow improving customer interaction without significantly expanding staff, contributing to more effective solutions to their problems, and improving service. This will simultaneously contribute to the growth of income of supplier organizations and improve the life quality of goods and services consumers.
Keywords: question-answering system, natural language processing, database, knowledge base, ontology, machine learning, pre-trained language models
For citation. Dorokhina G.V., Polous A.G. Methods of organizing question-answering systems. News of the Kabardino-Balkarian Scientific Center of RAS. 2024. Vol. 26. No. 6. Pp. 175–187. DOI: 10.35330/1991-6639-2024-26-6-175-187
References
- Lapshin V.A. Question-answering systems: development and prospects. Automatic Documentation and Mathematical Linguistics. 2012. No. 6. Pp. 1–9. EDN: PDWJEV. (In Russian)
- Ponomarev V.V., Tumanov V.E. Model of a digital interactive document in the systems analysis of subject ontology. Sistemnyy analiz v proyektirovanii i upravlenii [Systems analysis in design and management]: collection of scientific papers of the XXV International scientific and educational-practical conference, October 13–14, 2021, in 3 parts. Part 3. DOI: 10.18720/SPBPU/2/id21-361. (In Russian)
- Muromtsev D.I. Models and methods of individualization of e-learning in the context of the ontological approach. Ontology of Designing. 2020. Vol. 10. No. 1(35). Pp. 34–49. DOI: 10.18287/2223-9537-2020-10-1-34-49. (In Russian)
- Verevichev I.I. Logika: kratkiy teoreticheskiy kurs: uchebnoye posobiye dlya studentov gumanitarnykh fakul’tetov [Logic: a short theoretical course: a tutorial for students of humanities faculties]. Ulyanovsk: UlGTU, 2009. 101 p. (In Russian)
- Lopez V.Is, Uren V., Sabou M., Motta E. Question аnswering fit for the Semantic Web? Article in Semantic Web. DOI: 10.3233/SW-2011-0041. UK: Milton Keynes, 2011. Pp. 14–47.
- Tyurina D.A., Palmov S.V. Application of neural networks in natural language processing. Journal of Applied Research. 2023. No. 7. Pp. 158–162. DOI: 10.47576/2949-1878_2023_7_158. (In Russian)
- Chernomorova T.S., Vorobyov S.P. Classification and principles of constructing question-answer search systems. Bulletin of Science and Practice. 2020. Vol. 6. No. 8. Pp. 145–156. DOI: 10.33619/2414-2948/57/12. (In Russian)
- Dorodnykh N.O., Yurin A.Yu. An approach to automated filling of knowledge graphs with entities based on table analysis. Ontology of Designing. 2022. Vol. 12. No. 3(45). Pp. 336–352. DOI: 10.18287/2223-9537-2022-12-3-336-352. (In Russian)
- Vidiya A.V., Dorodnykh N.O., Yurin A.Yu. An approach to creating ontologies based on spreadsheets with an arbitrary structure. Ontology of Designing. 2021. Vol. 11. No. 2(40). Pp. 212–226. DOI: 10.18287/2223-9537-2021-11-2-212-226. (In Russian)
- Lomov P.A., Nikonorova M.L., Shishaev M.G. Extracting relations from NER-labeled sentences for ontology training. Trudy Kol’skogo nauchnogo tsentra RAN. Seriya: Tekhnicheskiye nauki [Proceedings of the Kola Science Center of the Russian Academy of Sciences. Series: Technical sciences]. 2022. Vol. 13. No. 2. Pp. 23–30. DOI: 10.37614/2949-1215.2022.13.2.002. (In Russian)
- Tikhobaeva O.Yu., Bruches E.P., Batura T.V. Extracting semantic relations from the texts of scientific articles. Vestnik NGU. Seriya: Informatsionnyye tekhnologii [Bulletin of NSU. Series: Information technologies]. Vol. 20. No. 3. Pp. 65–76. DOI 10.25205/1818-7900-2022-20- 3-65-76. (In Russian)
- Mezentseva A.A., Bruches E.P., Batura T.V. Methods and approaches to automatic linking of entities in Russian. Proceedings of The Institute for System Programming of the RAS. 2022. Vol. 34. No. 4. Pp. 187–200. DOI: 10.15514/ISPRAS-2022-34(4)-13. (In Russian)
- Golikov A.A., Akimov D.A., Romanovsky M.S., Trashchenkov S.V. Aspects of creating a corporate question-answering system using generative pre-trained language models. Litera. 2023. No. 12. Pp. 190–205. DOI: 10.25136/2409-8698.2023.12.69353. (In Russian)
- Derevyanko D.V., Palchunov D.E. Formal methods for developing a question-answering system in natural language. Vestnik Novosibirskogo gosudarstvennogo universiteta. Seriya: Informatsionnyye tekhnologii [Bulletin of the Novosibirsk State University. Series: Information Technology]. 2014. Vol. 12. No. 3. Pp. 34–47. EDN: RKCZKL. (In Russian)
- Milkova M.A., Nevolin I.V., Pigorev D.P. Modern methods for extracting key information from regulatory documents. Economics of Contemporary Russia. 2021. No. 2(93). DOI: 10.33293/1609-1442-2021-2(93)-101-114. (In Russian)
- Gulyaev P.A., Elistratova E.A., Konovalov V.P. et al. Tracking the state of a goal-oriented dialogue based on BERT. Proceedings of Moscow Institute of Physics and Technology. 2021. Vol. 13. No. 3(51). Pp. 48–61. DOI: 10.53815/20726759_2021_13_3_48. (In Russian)
- Favorskaya M.N., Andreev V.V. Adaptive block tensor decomposition in visual question-answering systems. Software & Systems. 2021. Vol. 34. No. 1. Pp. 164–171. DOI: 10.15827/0236-
235X.133.164-171. (In Russian) - Bali V., Verma A. A study on components, benchmark criteria and techniques used in ontology-based question answering systems. IJISAE, 2022. Vol. 10. No. 1s(2002). India: Chandigarh, 2022. Pp. 9–17.
Information about the author
Galina V. Dorokhina, Researcher, Department of Systems Analysis and Intelligent Interfaces, Institute
of Artificial Intelligence Problems;
283048, Russia, Donetsk, 118b Artema street;
SPIN-code: 6522-7758
Andrey G. Polous, Software Engineer, Department of Systems Analysis and Intelligent Interfaces,
Institute of Artificial Intelligence Problems;
283048, Russia, Donetsk, 118b Artema street;
student, Faculty of Physics and Technology, Donetsk State University;
283001, Russia, Donetsk, 24 University street;
SPIN-code: 6966-7988











