@TechReport{rpe--slovko-03,
author = {Roger Evans and Carole Tiberius and Dunstan Brown and Greville Corbett},
title = {Russian Lemmatisation with DATR},
year = {2003},
grant = {Supported by ESRC grant no. RES-000-23-0082 to Surrey University},
abstract = {
In this paper, we describe an approach to lemmatisation for Russian nouns, which makes use of a large-scale inheritance lexicon implemented in the lexical representation language DATR (Evans and Gazdar 1996). The lexicon was compiled semi-automatically from Zaliznjak's morphological dictionary (Zaliznjak 1977, Ilola and Mustajoki 1989) and automatically generates fully inflected forms together with their associated morphosyntax for around 40,000 Russian nouns. From this resource, we have automatically extracted wordform recognition rules and compiled them into a lemmatiser which hypothesises possible citation form and morphosyntactic features for nominal wordforms. We describe the construction of the lemmatiser and the results of our initial evaluation of its accuracy. },
month = {October},
note = {Presented at SLOVKO 2003, Bratislava}
}