Алгоритм работы морфологического парсера калмыцкого языка |
|
|
|
Written by: Виктория Васильевна Куканова, Араша Юрьевич Каджиев
|
Воскресенье, 07 Сентябрь 2014 |
This
article is devoted to the description of an algorithm for a morphological
parser of the Kalmyk language for automatic processing of texts. The work on
the creation and development of the National Corpus of the Kalmyk Language
began at the end of 2010 and now includes 17 million of tokens. The parser
analyzes about 90 percent of text including 11 % of homonym variants for morphological annotation.
Our aim is to increase the figure of non-ambiguous analysis.
kukanova-kadzhiev_elmanuscript2014 (718.34 kB)
|