Text Analysis and Correction Using Specialized Linguistic Habit Graphs LHG

• Autorzy: Gadamer, M. , Horzyk, A.
• Języki publikacji: EN

Abstrakty

EN

This paper introduces a novel linguistic habit graph LHG for automation of contextual text correction. The result of our current researches is a constructed mechanism for searching and aggregating tens of millions word-triples from websites that create a simple context statement for a given language that makes us able to predict word sequences and proceed corrections better than currently used solutions. Moreover, the LHG graph during colleting word-triples grow is limited and slows down so LHG graphs can be continuously supplemented by reading next texts to improve the correction results.

Słowa kluczowe

EN

graph LHG; automatic text correction; text editor

• Czasopismo: Image Processing & Communications
• Rocznik: 2012
• Tom: Vol. 17, no. 4
• Strony: 245--250
• Opis fizyczny: Bibliogr. 11 poz., rys.

Twórcy

autor

Gadamer, M.

• AGH University of Science and Technology, Mickiewicza Av. 30, 30-059 Cracow, Poland, Department of Automatics,

autor

Horzyk, A.

• AGH University of Science and Technology, Mickiewicza Av. 30, 30-059 Cracow, Poland, Department of Automatics

Bibliografia

• [1] S. Abney, Part-of-Speech Tagging and Partial Parsing, Corpusbased methods in language and speech processing, Vol. 2, pp. 1-23, 1996
• [2] A.M. Robertson, P. Willett, Applications of n-grams in textual information systems, Journal of Documentation, Vol. 54, pp. 48-69, 1998
• [3] M. Ganapathiraju, V. Manoharan, J. Klein- Seetharaman, Statistical Analysis of the Indus Script Using n-Grams, PLoS ONE, Vol. 5, No. 16, 2010
• [4] F.M. Suchanek, G. Ifrim, G. Weikum, Combining linguistic and statistical analysis to extract relations from web documents, Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining KDD 06, 712, 2006
• [5] S. Hunston, G. Francis, Pattern Grammar: A Corpus-Driven Approach to the Lexical Grammar of English, Computational Linguistics, Vol. 27, pp. 318-320, 2000
• [6] M. Gadamer, Automatyczna kontekstowa korekta tekstów z wykorzystaniem Grafu Przyzwyczajeń Lingwistycznych zbudowanego przez robota internetowego dla j˛ezyka polskiego, Praca magisterska
• [7] A. Horzyk,W oczekiwaniu na sztuczną˛ inteligencję˛, Software Developer’s Journal, ISSN 1734-3917, Vol. 4, pp. 10-17, 2011
• [8] M. Gadamer, A. Horzyk, Automatyczna kontekstowa korekta tekstów z wykorzystaniem grafu LHG, Computer Science AGH, Vol. 10, pp. 39-57, Kraków, 2010
• [9] Contextual spelling in the 2007 Microsoft Office system http://blogs.msdn.com/b/correcteurorthographiqueoffice/archive/2006/06/05/contextual-spelling-in-the-2007-microsoft-office-system.aspx
• [10] W. Lubaszewski, Słowniki komputerowe i automatyczna ekstrakcja informacji z tekstu, AGH Uczelniane wydawnictwa naukowo-dydaktyczne, Kraków 2009
• [11] J. Li, K. Ouazzane, H. Kazemian, Y. Jing, R. Boyd, A neural network based solution for automatic typing errors correction, Neural Computing & Applications, Vol. 20, No. 6, pp. 889-896, 2011