Artificial intelligence

Scientific journal

ISSN 2710-1673

ONLINE: ISSN 2710-1681

Select your language


Combining probabilistic tagging with rule-based multilevel chunking for requirements elicitation

Bazhenov N.1
1 National Technical University “Kharkov Polytechnical Institute”

Full text (PDF)

UDC: 519.876
Publication Language: English
Stuc. intelekt. 2010; 15(2):6-14

Abstract: In this paper author describes a multi-layered NLP approach for the elicitation of ontology relevant information from free requirements text. To automate the requirements elicitation process from textual information of stakeholders, as well as to transform it into structured and validated fashion the combination of probabilistic and rule-based NLP methods are proposed. The developed methodology includes a multi-level chunking strategy as its core principle.

Keywords:

References:

  1. Fliedl G. NIBA Project: Overview / G. Fliedl, Ch. Kop, J. Vöhringer, Ch. Winkler // ER 2005: 24th International Conference on Conceptual Modeling, Alpen-Adria-Universität Klagenfurt, 2005.
  2. Shekhovtsov V.A. Capturing the Semantics of Quality Requirements into an Intermediate Predesign Model / V.A. Shekhovtsov, Christian Kop, Heinrich C. Mayr // SIGSAND-EUROPE Symposium 2008. –Marburg, Germany, 2008. – P. 25-38.
  3. Manning C.D. Foundations of statistical natural language processing / C. Manning. – The MIT Press,1999. – 680 p.
  4. Oliver Mason’s. Webpages [Электронный ресурс] / O. Mason. – Режим доступа : http://www.english.bham.ac.uk/staff/omason/index.html.
  5. Schmid H. Probabilistic part-of-speech tagging using decision trees / H. Schmid // Proceedings of the International Conference on New Methods. – In Language Processing. – 1994.
  6. Brill E. Unsupervised learning of disambiguation rules for part of speech tagging / E. Brill // Proceedingsof the 3rd Workshop on Very Large Corpora. – 1995. – P. 1-13.
  7. Goldwater S. A fully Bayesian approach to unsupervised part-of-speech tagging / S. Goldwater, T. Griffiths // Proceedings of the 45th Annual Meeting of the ACL. – Prague, 2007. – P. 744-751.
  8. Mason O. Programming for Corpus Programming: how to do text analysis with Java / O. Mason. – Edinburgh University Press, 2000. – 224 p.
  9. Montylingua : a free, commonsense-enriched natural language understander [Электронный ресурс] –Режим доступа : http://web.media.mit.edu/~hugo/montylingua.
  10. Monty Klu Web v0.1 [Электронный ресурс]. – Режим доступа : http://montyklu.knospi.com.
  11. Bird S. Natural Language Processing in Python [Электронный ресурс] / S. Bird, E. Klein, E. Loper. –Режим доступа : http://nltk.org/doc/en/book.pdf.
  12. Weber G. NIBA Aspekte der Implementierung eines erweiterten Taggers für die automatische Textannotation in NIBA. Master Thesis / G. Weber. – Alpen-Adria-Universität Klagenfurt, 2007. – 114 p.
  13. Black C.A. A step-by-step introduction to the Government and Binding theory of a syntax [Электронныйресурс] / C.A. Black. – Режим доступа : http://www.sil.org/americas/mexico/ling/E002-IntroGB.pdf.
  14. Межуев В.И. Использование онтологий как предметных областей / В.И. Межуев // Искусственныйинтеллект. – 2009. – № 4. – С. 4-11.
  15. Звенигородский А.С. Концепция и задачи понимания смысла текста в системах искусственногоинтеллекта / А.С. Звенигородский // Искусственный интеллект. – 2009. – № 3. – С. 6-10.
  16. Шевченко О.Ю. Метод побудови інтелектуальних систем обробки інформації та документообігуза допомогою онтологічної бази знань / О.Ю. Шевченко, М.В. Климова // Искусственный интеллект. –2009. – № 2. – С. 91-97.

View full text (PDF)