Эксперименты по автоматическому разрешению лексико-семантической неоднозначности и выделению конструкций (на материале Национального корпуса русского языка)

С. 159–175.

Митрофанова О. А., Lyashevskaya O., Грачкова М. А., Шиморина А. С., Шурыгина А. С., Романов С. В.

The research project reported in this paper aims at automatic extraction of
linguistic information from contexts in the Russian National Corpus (RNC) and its subsequent use in building a comprehensive lexicographic resource – the Index of Russian lexical constructions. The proposed approach implies automatic context classification intended for word sense disambiguation (WSD) and construction identification (CxI). The automatic context processing procedure takes into account the following types of contextual information represented in the RNC multilevel annotation: lexical (lemma) tags (lex), morphological tags (gr), lexical-semantic (taxonomy) tags (sem), and combinations of the various types of tags. Multiple experiments on WSD and CxI are performed using RNC representative context samples. In each series of experiments we analyze (1) different context markers of meaning of target words and (2) constructions including context markers and target words.

Keywords: Национальный корпус русского языка, конструкции, разрешение лексико-семантической неоднозначности, выделение конструкций, классификация контекстов

In book

Структурная и прикладная лингвистика

Вып. 9. , СПб.: Издательство СПбГУ, 2012.