350 rub
Journal Highly available systems №2 for 2015 г.
Article in number:
Modern automatic text processing technologies
Keywords: automated text processing semantic analysis formal description of text semantic structure linguistic software declarative means
Authors:
Yu.P. Kalinin - Dr. Sc. (Eng.), Professor, Head of Laboratory, Institute of Informatics Problems, FRC CSC RAS. E-mail: upkalinin@mail.ru A. A. Khoroshilov - Dr. Sc. (Eng.), Leading Research Scientist, Institute of Informatics Problems, FRC CSC RAS; Professor, Moscow Aviation Institute (National Research University). E-mail: khoroshilov@mail.ru A.A. Khoroshilov - Ph. D. (Eng.), Research Scientist, Institute of Informatics Problems, FRC CSC RAS. E-mail: alex_khoroshilov@mail.ru
Abstract:
The development of automated information technology depends on achievements in the study of human thinking, processes of speech communication between people and computer-based simulation of these processes. The stable phraseological word combinations are the principal means for expression of concept names in texts. The natural language is an universal means of perception, accumulation, storage and transmission of information. The text processing technologies should be universal, because the natural language is an universal means for communication and encompasses all areas of human activity. Today, the most popular procedures for semantic text information processing are: 1. Automatic classification, indexing and abstracting of documents. 2. Automatic recognition of semantic proximity of documents. 3. Machine translation of texts from one natural language to another. 4. Information search in monolingual and multilingual data bases using queries formulated in natural languages. 5. In-depth analytical and synthetic text processing and gaining of generalized information on its basis. In order to develop automated information technologies it is necessary to solve three problems: 1. Identify the conceptual structure of natural languages. 2. Identify the most stable out-of-context associative semantic relations between concepts. 3. Develop and modernize the basic procedures of semantic and syntactic analysis and synthesis of texts.
Pages: 19-34
References

 

  1. ISC-13 Post-Conference Summary (2013). www.isc-events.com/isc13/
  2. www.top500.org/
  3. Goldman N., Bertone P., Chen S., Dessimoz C.et al Towards practical, high-capacity, low-maintenance information storage in synthesized DNA. Nature494. P. 77−80. (07 February 2013). doi:10.1038/nature11875.
  4. Novaja filosofskaja ehnciklopedija. M.: Mysl. 2000. T. 2.
  5. Spirkin A.G. Filosofija (izdanie vtoroe). M.: Gardariki. 2006.
  6. Belonogov G.G., Giljarevskijj R.S. Eshhe raz o gnoseologicheskom statuse ponjatija «informacija» // Nauchno-tekhnich. informacija. Serija 2. M.: VINITI. 2010. № 2.
  7. Belonogov G.G.Teoreticheskie problemy informatiki.T. 2.Semanticheskieproblemy informatiki / Pod obshhejj red. K.I. Kurbakova. M.: REHA im. G.V. Plekhanova. 2008.
  8. Maksimenko S.D. Obshhaja psikhologija. Kiev: Refl-buk. Vakler. 2000.
  9. Ferdinand de Sossjur. Kurs obshhejj lingvistiki. M.: Progress. 1977.
  10. Belonogov G.G., Giljarovskijj R.S., KHoroshilov A.A. Problemy avtomaticheskojj smyslovojj obrabotki tekstovojj informacii // Nauchno-tekhnich. informacija. Ser. 2. Informacionnye processy i sistemy. Vseros. institut nauchnojj i tekhnicheskojj informacii RAN. 2012.
  11. Belonogov G.G., Giljarevskijj R.S., KHoroshilov Al-dr A., KHoroshilov Al-ejj A. Razvitie sistem avtomaticheskojj obrabotki tekstovojj informacii // Nejjrokompjutery: razrabotka, primenenie. 2010. № 8.
  12. Belonogov G.G., KHoroshilov Al-dr A., KHoroshilov Al-sejj A. Edinicy jazyka i rechi v sistemakh avtomaticheskojj obrabotki tekstovojj informacii // Nauchno-tekhnich. informacija. Ser. 2. M.: VINITI. 2005. № 11.
  13. Zvegincev V.A. Predlozhenie i ego otnoshenie k jazyku i rechi. M.: Izdatelstvo Moskovskogo universiteta. 1976.
  14. Belonogov G.G., Giljarevskijj R.S., KHoroshilov Al-sejj Al-drovich, KHoroshilov Al-sejj Al-seevich Avtomaticheskoe raspoznavanie smyslovojj blizosti dokumentov // Nauchno-tekhnich. informacija. Ser. 2. M.: VINITI. 2011. № 9.
  15. www.google.com/press/podium/ana/html.
  16. Belonogov G.G., Giljarevskijj R.S., Seletkov S.N., KHoroshilov A.A. O putjakh povyshenija kachestva poiska tekstovojj informacii v sisteme Internet //Nauchno-tekhnich. informacija. Ser. 2. M.: VINITI. 2013. № 8.
  17. Melnikov V.O., Maksimov O.A., Melikjan G.S. KHarakteristika informacionno-poiskovykh sistem Internet: teoreticheskie i prakticheskie aspekty //Nauchno-tekhnich. informacija. Ser. 2. M.: VINITI. 2009. № 2.
  18. www.compress.ru/article.aspx-id=23469&iid=1080.
  19. www.tadviser.ru/index.php.
  20. www.statsoft.ru/products/Enterprise/big-data.php.
  21. Bogdanov JU.M., Poshataev O.N., KHoroshilov A.A. Principy sozdanija vysokoproizvoditelnykh sistem obrabotki i analiza tekstovojj informacii // Nauchno-tekhnich. informacija. Ser. 2. M.: VINITI. 2013. № 12.
  22. ZHukov D.A. My perevodchiki. M.: Znanie. 1975.
  23. Nagao M. A framework of a mechanical translation between Japanese and English by analogy principle, in Artificial and Human Intelligence / ed. A. ElithornandR Banerji.NorthHolland. 1984.P. 173−180.
  24. Webb Lynn E. Advantages and Disadvantages of Translation Memory: Cost/Benefit Analysis. SanFranciscoStateUniversity. 1992.
  25. Belonogov G.G., KHoroshilov Al-dr A., KHoroshilov Al-sejj A., Kozachuk M.V., Ryzhova E.JU., Guskova L.JU. Kakim byt mashinnomu perevodu v KHKHI veke. Sb. «Perevod: tradicii i sovremennye tekhnologii». M.: VCP. 2002.
  26. www.lernolibro.info/artikoloj/artikolo.php-nomo=20.2.
  27. Belonogov G.G., Al-dr A. KHoroshilov, Al-sejj A. KHoroshilov. Avtomatizacija sostavlenija anglo-russkikh dvujazychnykh frazeologicheskikh slovarejj po massivam dvujazychnykh tekstov (bilingv) // Nauchno-tekhnich. informacija.. Ser. 2. M.: VINITI. 2010. № 5.
  28. KHoroshilov Al-dr. A., KHoroshilov Al-ejj A. i dr. Programmnyjj kompleks «Avtomatizirovannoe sostavlenie dvujazychnykh slovarejj po parallelnym tekstam dlja sistemy MetaFraz (MetaFrazACD)» / Svidetelstvo ob oficialnojj registracii programm dlja EHVM № 2014611770 ot 10 fevralja 2014 g.
  29. KHoroshilov Al-dr. A., KHoroshilov Al-ejj A. i dr. Programmnyjj kompleks «Avtomatizirovannaja slovarnaja sluzhba MetaFraz (MetaFrazADS)» / Svidetelstvo ob oficialnojj registracii programm dlja EHVM № 2014612497 ot 26 fevralja 2014 g.
  30. KHoroshilov Al-dr. A., KHoroshilov Al-ejj A. i dr. Sistema perevoda MetaFraz R10 (MFTranslationSystemR10)» / Svidetelstvo ob oficialnojj registracii programm dlja EHVM № 2014663082 ot 15 dekabrja 2014 g.
  31. KHoroshilov Al-dr. A., KHoroshilov Al-ejj A. i dr. Nadstrojjki sistemy perevoda MetaFraz R10 (MFLingwareAdd-inR10)» / Svidetelstvo ob oficialnojj registracii programm dlja EHVM № 2014662528 ot 02 dekabrja 2014 g.
  32. KHoroshilov Al-dr. A., KHoroshilov Al-ejj A. i dr. Lingvisticheskijj kompleks MetaFraz R10 (MFLingwareComplexnR10)» / Svidetelstvo ob oficialnojj registracii programm dlja EHVM № 2014663079 ot 15 dekabrja 2014 g.
  33. KHoroshilov Al-dr. A., KHoroshilov Al-ejj A. i dr. Sistema semanticheskojj obrabotki tekstov MetaFraz R10 (MFTextAnalystR10)» / Svidetelstvo ob oficialnojj registracii programm dlja EHVM № 2014663081 ot 15 dekabrja 2014 g.
  34. KHoroshilov Al-dr. A., KHoroshilov Al-ejj A. i dr. Server lingvisticheskogo PO MetaFraz R10 (MFLingwareServerR10)» / Svidetelstvo ob oficialnojj registracii programm dlja EHVM № 2014662743 ot 08 dekabrja 2014 g.
  35. KHoroshilov Al-dr. A., KHoroshilov Al-ejj A. i dr. Lingvisticheskijj integracionnyjj komplekt MetaFraz R10 (MFLingwareIntegrationKitR10)» / Svidetelstvo ob oficialnojj registracii programm dlja EHVM № 2014662529 ot 02 dekabrja 2014 g.