This article is cited in 1 paper

Intellectual analysis of data on the basis of Stanford CoreNLP for pos tagging of texts in the Russian language

O. V. Andreeva, M. B. Bagirov, A. A. Dankina, T. O. Fedorova, M. M. Sheveleva

R. E. Alekseev Nizhny Novgorod State Technical University; 24-1 Minin Str., Nizhny Novgorod 603000, Russian Federation

Abstract: The basic principles of Stanford CoreNLP and the implementation of this library in various natural languages are discussed. Different ways of Stanford CoreNLP interaction with texts in Russian have been developed. A model that makes it possible to determine the parts of speech in the texts in Russian has been created, the quality of the model's performance on the texts of technical literature in Russian has been increased. The tests that show the effectiveness of the implemented changes are presented.

Keywords: data processing; intellectual data analysis; Stanford CoreNLP; natural language analysis; POS tagger; definition of parts of speech; morphological analysis of texts in the Russian language.

Received: 23.10.2017

DOI: 10.14357/08696527180211

Bibliographic databases:

•