Advertisement

Developing Conversational Natural Language Interface to a Database

  • Boris Galitsky
Chapter

Abstract

In this Chapter we focus on a problem of a natural language access to a database, well-known and highly desired to be solved. We start with the modern approaches based on deep learning and analyze lessons learned from unusable database access systems. This chapter can serve as a brief introduction to neural networks for learning logic representations. Then a number of hybrid approaches are presented and their strong points are analyzed. Finally, we describe our approach that relies on parsing, thesaurus and disambiguation via chatbot communication mode. The conclusion is that a reliable and flexible database access via NL needs to employ a broad spectrum of linguistic, knowledge representation and learning techniques. We conclude this chapter by surveying the general technology trends related to NL2SQL, observing how AI and ML are seeping into virtually everything and represent a major battleground for technology providers.

References

  1. Agrawal S, Chaudhuri S, Das G (2002) Dbxplorer: a system for keyword-based search over relational databases. In: ICDE, pp 5–16Google Scholar
  2. Androutsopoulos I, Ritchie GD, Thanisch P (1995) Natural language interfaces to databases – an introduction. Nat Lang Eng 1(1):29–81CrossRefGoogle Scholar
  3. Bahdanau D, Cho K, Bengio Y (2015) Neural machine translation by jointly learning to align and translate. In: Proceedings of the ICLR, San Diego, CaliforniaGoogle Scholar
  4. Berant J, Chou A, Frostig R, Liang P (2013) Semantic parsing on freebase from question-answer pairs. In: EMNLP, pp 1533–1544Google Scholar
  5. Bergamaschi S, Guerra F, Interlandi M, Lado RT, Velegrakis Y (2013) Quest: a keyword search system for relational data based on semantic and machine learning techniques. PVLDB 6(12):1222–1225Google Scholar
  6. Cearley DW (2017) Assess the potential impact of technology trends. https://www.gartner.com/doc/3823219?ref=AnalystProfile&srcId=1-4554397745
  7. Chambers J (2014). Are you ready for the internet of everything? World Economic Forum, from https://www.weforum.org/agenda/2014/01/are-you-ready-for-the-internet-of-everything/ (15 Jan 2014)
  8. Dong L, Lapata M (2016) Language to logical form with neural attention. ACLGoogle Scholar
  9. Galitsky B (2003) Natural language question answering system: technique of semantic headers. Advanced Knowledge International, AustraliaGoogle Scholar
  10. Galitsky B (2005) Natural language front-end for a database. Encyclopedia of database technologies and applications, p 5. IGI Global Pennsylvania USAGoogle Scholar
  11. Galitsky B, S Botros (2012) Searching for associated events in log data. US Patent 8,306,967Google Scholar
  12. Galitsky B, M Grudin (2001) System, method, and computer program product for responding to natural language queries. US Patent App. 09/756,722Google Scholar
  13. Galitsky B and Parnis A (2019) Accessing Validity of Argumentation of Agents of the Internet of Everything. In Lawless, W.F., Mittu, R., Sofge, D., and ·Russell, S., Artificial Intelligence for the Internet of Everything. Elsevier, AmsterdamGoogle Scholar
  14. Galitsky B, D Usikov (2008) Programming Spatial Algorithms in Natural Language. AAAI Workshop Technical Report WS-08-11.–Palo Alto, pp 16–24Google Scholar
  15. Galitsky B, Dobrocsi G, De La Rosa JL, Kuznetsov SO (2010) From generalization of syntactic parse trees to conceptual graphs. In: International conference on conceptual structures, pp 185–190Google Scholar
  16. Galitsky B, De La Rosa JL, Dobrocsi G (2011) Mapping syntactic to semantic generalizations of linguistic parse trees. In: Proceedings of the twenty-fourth international Florida artificial intelligence research society conferenceGoogle Scholar
  17. Galitsky B, D Ilvovsky, F Strok, SO Kuznetsov (2013a) Improving text retrieval efficiency with pattern structures on parse thickets. In: Proceedings of FCAIR, pp 6– 21Google Scholar
  18. Galitsky B, Kuznetsov SO, Usikov D (2013b) Parse thicket representation for multi-sentence search. In: International conference on conceptual structures, pp 153–172Google Scholar
  19. Goldberg Y (2015) A primer on neural network models for natural language processing. CoRR, abs/1510.00726Google Scholar
  20. Kate RJ, Wong YW, Mooney RJ (2005) Learning to transform natural to formal languages. In: AAAI, pp 1062–1068Google Scholar
  21. Kupper D, Strobel M, Rosner D (1993) Nauda – a cooperative, natural language interface to relational databases. In: SIGMOD conference, pp 529–533Google Scholar
  22. Li FH, Jagadish V (2014) Nalir: an interactive natural language interface for querying relational databases. In: VLDB, pp 709–712Google Scholar
  23. Li F, Jagadish HV (2016) Understanding natural language queries over relational databases. SIGMOD Record 45:6–13CrossRefGoogle Scholar
  24. Li Y, Yang H, Jagadish HV (2005) Nalix: an interactive natural language interface for querying xml. In: SIGMOD conference, pp 900–902Google Scholar
  25. Li Y, Yang H, Jagadish HV (2006) Constructing a generic natural language interface for an XML database. In: EDBT, pp 737–754Google Scholar
  26. Liang P, Potts C (2015) Bringing machine learning and compositional semantics together. Ann Rev Linguis 1(1):355–376CrossRefGoogle Scholar
  27. Mikolov T, Chen K, Corrado GS, Dean J (2015). Computing numeric representations of words in a high-dimensional space. US Patent 9,037,464, Google, IncGoogle Scholar
  28. Munro K. (2017, 5/23), How to beat security threats to ‘internet of things’. From http://www.bbc.com/news/av/technology-39926126/how-to-beat-security-threats-to-internet-of-things
  29. Nihalani MN, Silakari DS, Motwani DM (2011) Natural language Interface for database: a brief review. Int J Comput Sci Issues 8(2)Google Scholar
  30. Popescu A-M, Etzioni O, Kautz HA (2003) Towards a theory of natural language interfaces to databases. In: IUI, pp 149–157Google Scholar
  31. Popescu A-M, Armanasu A, Etzioni O, Ko D, Yates A (2004) Modern natural language interfaces to databases: composing statistical parsing with semantic tractability. In: COLINGGoogle Scholar
  32. Quirk C, Mooney R, Galley M (2015) Language to code: learning semantic parsers for if-this-then-that recipes. In: ACL, pp 878–888Google Scholar
  33. Stankovic JA (2014) Research directions for the internet of things. IEEE Internet Things J 1(1):3–9MathSciNetCrossRefGoogle Scholar
  34. Suri N, Tortonesi M, Michaelis J, Budulas P, Benincasa G, Russell S, Winkler R (2016) Analyzing the applicability of internet of things to the battlefield environment. In: Military communications and information systems (ICMCIS), 2016 international conference on. IEEE, pp 1–8Google Scholar
  35. Yaghmazadeh N, Wang Y, Dillig I and Dillig T (2017) SQLizer: Query synthesis from natural language. Proceedings of the ACM on Programming Languages, 1:63:1–63:26Google Scholar
  36. Zaremba W, Sutskever I, Vinyals O (2015) Recurrent neural network regularization. In: Proceedings of the ICLR, San Diego, CaliforniaGoogle Scholar
  37. Zhong V, Xiong C, Socher R (2017) Seq2SQL: generating structured queries from natural language using reinforcement learning. https://arxiv.org/pdf/1709.00103.pdf

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Boris Galitsky
    • 1
  1. 1.Oracle (United States)San JoseUSA

Personalised recommendations