РАЗРЕШЕНИЕ ГРАММАТИЧЕСКОЙ МНОГОЗНАЧНОСТИ В КОРПУСЕ ТАТАРСКОГО ЯЗЫКА
GRAMMATICAL DISAMBIGUATION IN THE CORPUS OF THE TATAR LANGUAGE
Author(s): Bulat Ernstovich Khakimov, Rinat Abrekovich Gilmullin, Ramil Raisovich GataullinSubject(s): Language studies, Language and Literature Studies, Theoretical Linguistics, Morphology, Lexis, Eastern Slavic Languages, Philology
Published by: Казанский (Приволжский) федеральный университет
Keywords: corpus of a language; Tatar language; grammatical homonymy; homoform; disambiguation;
Summary/Abstract: This paper deals with the corpus-based study of the most frequent types of grammatical homonymy in the Tatar language and the possibilities to automate disambiguation in the corpus. We determine the relevance of alternative parses generated in the process of automatic morphological analysis in terms of the real language ambiguity. We propose a classification of frequent homoforms and methods for homonymy resolution and also estimate the potential effect of resolution of these types of grammatical ambiguity for the corpus.
Journal: Ученые записки Казанского университета. Серия Гуманитарные науки
- Issue Year: 156/2014
- Issue No: 5
- Page Range: 236-244
- Page Count: 9
- Language: Russian
