Multi-agent Question-Answering System

  • Anastasia MochalovaEmail author
  • Vladimir Mochalov
Conference paper


The paper suggests an approach to the design of a question-answering system based on the interaction of various agents whose work is aimed at obtaining the answer most relevant to the user’s request. The types of such agents, the principles of their work, their functions, the ways of interaction for obtaining the final answer are described. A distinctive feature of the described approach to the implementation of the multi-agent question-answering system is that among the agents providing the system operation, there are those using the machine data and the logical conclusions, as well as those whose main function is to communicate with people and receive the necessary information from them. Thus, the efficiency of such a system is largely determined by the fact that the system uses the most powerful intellectual resources—humans—along with the machine resources and algorithms. A peculiar feature of the question-answering system described in the paper is that the agents ensuring the system operation interact with each other, as well as with users in natural language.


Question-answering systems Intelligent agents Automatic text processing 


  1. 1.
    Mochalova AV (2017) The semantic analyzer of the Russian-language text for the question-answer system. Ph.D. dissertation, Petrozavodsk State University, 129 pGoogle Scholar
  2. 2.
    Lehnert W (1977) The process of question answering. Ph.D. dissertation, research report. No. 88. Yale UniversityGoogle Scholar
  3. 3.
    Graesser A (1994) Question asking during tutoring. Am Educ Res J 31:104–137CrossRefGoogle Scholar
  4. 4.
    Lapshin VA (2012) Question-answer systems: development and prospects. Sci Tech Inf Inf Process Syst 6:1–9Google Scholar
  5. 5.
    Cai L, Zhou G, Liu K et al (2011) Large-scale question classification in cQA by leveraging Wikipedia semantic knowledge. In: Proceedings of ACM CIKM, ACM, New York, pp 1321–1330Google Scholar
  6. 6.
    Huang Z, Thint M, Qin Z (2008) Question classification using head words and their hyperonims. EMNLP 927–936Google Scholar
  7. 7.
    Laokulrat N (2013) A survey on question classification techniques for question answering. KMITL Inf Technol J 2(1)Google Scholar
  8. 8.
    Roberts K, Masterton K, Fiszman M et al (2014) Annotating question types for consumer health questions. LREC workshop on building and evaluating resources for health and biomedical text processingGoogle Scholar
  9. 9.
    Sundblad H (2007) Question classification in question answering systems. Ph.D. dissertation, Linkopings UniversityGoogle Scholar
  10. 10.
    Scott S, Gaizauskas R (2001) QA-LaSIE: a natural language question answering system. In: Proceedings of the 14th biennial conference of the Canadian society on computational studies of intelligence, pp 172–182CrossRefGoogle Scholar
  11. 11.
    Rubashkin VS, Kapustin VA (2008) Use of definitions of terms in encyclopaedic dictionaries for automated ontology replenishment. In: XI all-Russian joint conference “internet and modern society”, St. PetersburgGoogle Scholar
  12. 12.
    Hovy E, Knight K, Junk M Large resources. Ontologies (SENSUS) and Lexi-cons.
  13. 13.
    Aramaki E, Imai T, Kashiwagi M, Kajino M, Miyo K, Ohe K (2005) Toward medical ontology using natural language processing.
  14. 14.
    Rubashkin VS (2013) Ontological semantics, knowledge, ontologies, ontologically oriented methods of information analysis of texts. FIZMATLIT, MoscowGoogle Scholar
  15. 15.
    Zakharov VP, Mochalova AV, Mochalov VA (2016) Ontology Modification Using Ontological-Semantic Rules. ICACT Trans Adv Commun Technol (TACT) 5(5):902–906Google Scholar
  16. 16.
    Answers database.
  17. 17. answers.
  18. 18.
    Zolotova GA (1988) Syntactic dictionary. The repertoire of the elementary units of Russian syntax (in Russian). Moscow, Russia: NaukaGoogle Scholar
  19. 19.
    Kaushinis TV, Kirillov AN, Korzhitsky NI, Krizhanovsky AA, Pilinovich AV, Sikhonina IA, Spirkova AM, Starkova VG, Stepkina TV, Tkach SS, Chirkova JV, Chuharev AL, Shorets DS, Yankevich DY, Yaryshkina EA (2015) A review of word-sense disambiguation methods and algorithms: introduction (in Russian). In: Proceedings of KarRC RAS. No. 10. Ser. mathematical modeling and information technologies, pp 69–98Google Scholar
  20. 20.
    Navigli R (2009) Word sense disambiguation: A survey. ACM Comput Surv (CSUR) 41(2, Article 10)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Institute of Cosmophysical Research and Radio Wave Propagation FEB RASKamchatka Region, Elizovskiy, ParatunkaRussia

Personalised recommendations