[RUS][ENG]

Series 9

PHILOLOGY. ASIAN STUDIES. JOURNALISM.

Issue 1, 2014

CONTENTS

Section LINGUISTICS
Codes UDC 81’32, 81’322.2, 811.161.1 Page 161-166
Title MORPHOLOGICAL TAGGING OF VARIATIVE TEXT WITH NOOJ FOR NLP (EVIDENCE FROM “THE TALE OF THE ROUT OF MAMAI”)
Author 1 Kovrigina Liubov Yu. St. Petersburg State University
7/9, Universitetskaya nab., St. Petersburg, 199034, Russian Federation
post-graduate student
e-mail: lkovriguina@gmail.com
Summary Variative texts of considerable length exist only in medieval literature and disappear in the Modern period (simultaneously with extrusion of collective authorship and manuscript tradition). Within this article, textual variation is defined as variation of the text’s form (graphical, grammatical, lexical, etc. variation, as well as variation in the number and succession of episodes). Versions and copies of such texts contain numerous spelling and grammatical variants, some of which can not be easily identifi ed, that impede its’ automatic morphological analysis. Some capabilities of the free linguistic development environment Nooj regarding corpus processing and morphological tagging are explicated and illustrated on the textual variants of “The Tale of the Rout of Mamai”.
Keywords textual variation, lemmatization, natural language processing, corpus linguistics, “The Tale of the Rout of Mamai”.