350 rub
Journal Information-measuring and Control Systems №3 for 2015 г.
Article in number:
Improving the efficiency of contextual search in natural language
Authors:
E.A. Lupanova - Senior Lecturer, Nizhny Novgorod State Technical University n.a. R.E. Alekseev. E-mail: ealupano-va@yandex.ru S.L. Morugin - Head of Department, Nizhny Novgorod State Technical University n.a. R.E. Alekseev. E-mail: smoru-gin@yandex.ru
Abstract:
The problem of query processing when dealing with information search and retrieval systems. We propose a method for optimizing the search context in the formulation of questions in natural language. When working with the reference, search and expert systems of top priority for a satisfactory result is the ability to properly formulate the request. The request may be submitted in the form of formalized form, a set of keywords or a question in natural language. We propose to combine in a single system the opportunity to ask a question in natural language and the existence of formal requests. For each request, drawn up as a formalized way, the question is formulated on a natural-language. Then in automatic mode is formulated set of equivalent questions for each reference question. For creating equivalents used ambiguous context-free grammar, ontology, dictionary word forms and synonyms The result will be obtained set of equivalent questions. We show the distribution of the frequency of words in a set of equivalent issues and the distribution of frequencies of oc-currence of equivalent queries. We show, what occurrence of questions in search organization in which the first equivalents with the highest frequency of occurrence and higher probability of correct recognition, reduces the quantitative comparisons of finding in 3-7 times com-pared with the full search equivalents. Introduction right question equivalents allows you to make context search more flexible and faster with maximum facilities to the user in a natural language.
Pages: 63-68
References

 

  1. Loukachevitch N.V., Dobrov B.V., Chetviorkin I.I. RuThes-Lite, a Publicly Available Version of Thesaurus of Russian Language RuThes // MaterialyezhegodnojjMezhdunar. konf. «Dialog» «Kompjuternaja lingvistika i intellektualnye tekhnologii» (Bekasovo, 4-8 ijunja 2014 g.). Vyp. 13 (20). M.: Izd-vo RGGU. 2014. S. 340-349.
  2. Lukashevich N.V.Tezaurusy v zadachakh informacionnogo poiska. M.: Izdatelstvo MGU. 2011. 512 s.
  3. Boguslavskijj I., Dikonov V., Timoshenko S. Ontologija dlja podderzhki zadach izvlechenija smysla iz teksta na estestvennom jazyke: http://www.iitp.ru/upload/publications/6612/Ontology.pdf.
  4. Konstantinova N.S., Mitrofanova O.A. Ontologii kak sistemy khranenija znanijj: http://www.ict.edu.ru/ft/005706/ 68352e2-st08.pdf.
  5. Smirnov I.V., SHelmanov A.O. Semantiko-sintaksicheskijj analiz estestvennykh jazykov. CH. I. Obzor metodov sintaksicheskogo i semanticheskogo analiza tekstov // Iskusstvennyjj intellekt i prinjatie reshenijj. 2013. № 1. S. 41-54.
  6. Sochenkov I.V. Metod sravnenija tekstov dlja reshenija poiskovo-analiticheskikh zadach // Iskusstvennyjj intellekt i prinjatie reshenijj. 2013. № 2. S. 32-43.
  7. Romanenko A.A.Klasterizacija kollekcii tekstov // Mashinnoe obuchenie i analiz dannykh. 2012. T. 1. № 3. S. 305-310.
  8. Orlov JU.K.Nevidimaja garmonija: http://www.opentextnn.ru/music/interpretation/?id=2503.
  9. Morugin S.L. Opredelenie informacionnojj emkosti tekstovykh uchebnykh materialov na osnove associativnojj semanticheskojj seti // Trudy NGTU. Sistemy obrabotki informacii i upravlenija. Vyp. 16. N. Novgorod: NGTU. 2009. T. 76. S. 77-81.
  10. Baranov V.G., Milov V.R., Alipova N.A., Egorov JU.S.Podkhod k predstavleniju materialov v informacionno-obuchajushhikh sistemakh // Informacionno-izmeritelnye i upravljajushhie sistemy. 2013. T. 11. № 7. S. 19-23.
  11. Egorov JU.S., Alipova N.A., Musonov V.V. Strukturirovanie i predstavlenie kontenta v informacionno-spravochnykh i analiticheskikh sistemakh // Informacionno-izmeritelnye i upravljajushhie sistemy. 2013. T. 11. № 7. S. 33-36.