THE RUSSIAN LANGUAGE PIPELINE IN THE LIMA MULTILINGUAL ANALYZER

Victor Bocharov, Gaël de Chalendar

Abstract:

In this paper we describe the implementation of Russian language pipeline
in LIMA multilingual analyzer and the results obtained in GramEval-2020 shared
task. LIMA is a modular pipeline that implements rule-based and machine learn-
ing analysis components. Russian language pipeline includes deep neural net-
works based modules for tokenization, sentence segmentation, part of speech
tagging, lemmatization and dependency parsing. Part of speech tags, feature
tags and dependency trees conform to Universal Dependencies rules.