Please use this identifier to cite or link to this item:
|Title:||Hidden Markov model approach for non-sequential data in word sense disambiguation task|
|Keywords:||ЭБ БГУ::ЕСТЕСТВЕННЫЕ И ТОЧНЫЕ НАУКИ::Математика|
|Abstract:||Hidden Markov Models (HMMs) have been successfully used in many fields of science and have a variety of applications. Traditionally, HMMs have been applied to sequential data. But there are tasks (a word sense disambiguation in Natural Language Processing is one of them) when observation data are not sequential. In this article we present an adaptation algorithm for an HMM usage with data represented in the form of a directed acyclic graph.|
|Appears in Collections:||Chapter 8. NATURAL LANGUAGE PROCESSING|
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.