System for automatic morphological analysis of Russian
Also: automatic morphological generation of Russian,
beta version (see
below)
Go to the personal page of Grigori Sidorov.
Go to the personal page of Alexander
Gelbukh.
This is a program that performs lemmatization and provides grammar
information of each form. See detailed description below.
The system is an EXE file for Windows. DLL is available on request.
LICENSE:
- You can use
this program freely for academic purposes. No warranty.
- You should
inform us about the usage of the program, and
- You should
cite the corresponding paper in your publications obtained with the help
of the program (We would be grateful if you inform us about such
citations).
Paper for
citing:
A. Gelbukh, G. Sidorov.
Approach to construction of automatic morphological analysis
systems for inflective languages with little effort. In: Computational
Linguistics and Intelligent Text Processing (CICLing-2003), Lecture Notes in
Computer Science, N 2588, Springer-Verlag, 2003, pp.
215–220; www.cic.ipn.mx/~sidorov/GelbukhSidorovMorphCICLING2003.ps
Download:
Downloading means that you
accept the license. Thank you.
NEW: Version August 18, 2011. Bug related with line length fixed.
Download
the system for analysis
Detailed description of the system for automatic morphological analysis
of Russian:
The input file is any standard
text file (mind the encoding).
Output can be either
individual files with a prefix “c_” or a common file for all input files.
The output has the format: word lemma1 [info1] lemma2 [info2] ...
There are three possible formats
of grammar info for output: English, Russian Short and Russian Long (the last
two differs in the quantity of the grammar information added).
Example of the English output:
·
большой
большой [Adj, Full, Abl, Sg, Fem, ]
большой [Adj, Full, Acc, Sg, Masc, ]
большой [Adj, Full, Dat, Sg, Fem, ]
большой [Adj, Full, Gen, Sg, Fem, ]
большой [Adj, Full, Nom, Sg, Masc, ]
большой [Adj, Full, Prep, Sg, Fem, ]
·
стол
стол [Noun, Acc, Sg, Masc, Unanim, ]
стол [Noun, Nom, Sg, Masc, Unanim, ]
·
был
быть [Verb, Indic, Past, Sg, Masc, ]
·
у
у [Interj, ] у [Noun, unchanging ] у [Preposition, ]
·
окна
окно [Noun, Acc, Pl, Neutr, Unanim, ]
окно [Noun, Gen, Sg, Neutr, Unanim, ]
окно [Noun, Nom, Pl, Neutr, Unanim, ]
Example of the Russian Short
output:
·
большой
большой
[полн.,дат.п.,ед.ч.,жен.р.,]
большой
[полн.,вин.п.,ед.ч.,муж.р.,]
большой
[полн.,род.п.,ед.ч.,жен.р.,]
большой
[полн.,им.п.,ед.ч.,муж.р.,]
большой
[полн.,пр.п.,ед.ч.,жен.р.,]
большой
[полн.,тв.п.,ед.ч.,жен.р.,]
·
и
и [частиц.,] и
[межд.,] и
[неизм.,] и [союз,]
·
. . [.]
·
Долго
долгий
[кратк.,ед.ч.,ср.р.,]
долго [нареч.,]
·
быстро
быстрый
[кратк.,ед.ч.,ср.р.,]
·
Стол
стол
[вин.п.,ед.ч.,]
стол [им.п.,ед.ч.,]
·
был
быть
[изъяв.,прош.вр.,ед.ч.,муж.р.,]
·
у
у [межд.,] у
[неизм.,] у
[предл.,]
·
окна
окно
[вин.п.,мн.ч.,]
окно
[род.п.,ед.ч.,]
окно [им.п.,мн.ч.,]
Example of the Russian Long
output:
·
большой
большой
[Прил., полн.,
Дат. п., ед. ч.,
жен. р., ]
большой
[Прил., полн.,
Вин. п., ед. ч.,
муж. р., ] большой
[Прил., полн.,
Род. п., ед. ч.,
жен. р., ]
большой
[Прил., полн., Им.
п., ед. ч., муж. р., ]
большой
[Прил., полн., Пр.
п., ед. ч., жен.
·
Долго
долгий [Прил.,
кратк., ед. ч., ср.
р., ] долго [Наречие,
]
·
и
и [Частица, ] и
[Междометие, ]
и [Союз, ] и [Сущ.,
неизмен ]
·
быстро
быстрый
[Прил., кратк.,
ед. ч., ср. р., ]
·
. .
[.]
·
Стол
стол [Сущ., Вин.
п., ед. ч., муж. р.,
неод., ] стол
[Сущ., Им. п., ед. ч., муж.
р., неод., ]
·
был
быть [Гл.,
изъяв. накл.,
прош. вр., ед. ч.,
муж. р., ]
·
у
у
[Междометие, ]
у [Предлог, ] у
[Сущ., неизмен ]
- окна
окно [Сущ.,
Вин. п., мн. ч., ср.
р., неод., ] окно
[Сущ., Род. п., ед.
ч., ср. р., неод., ]
окно [Сущ., Им.
п., мн. ч., ср. р.,
неод., ]
Interface:
Automatic morphological generation of Russian (beta
version)
Download:
Downloading means that you
accept the license. Thank you.
Download the
system for generation
Examples
Examples of input data encoding (see also the
example file “encode.pas”):
NMUNS Noun, Masculine, Unanimated, Nominative, Singular
// Masculine and Unanimated
are taken from the dicitonary for nouns, so these
two letter are ignored
NFAGP Noun, Feminine, Animated, Genitive, Plural // Feminine and Animated are taken from the
dicitonary for nouns, so these two letter are ignored
AFNSM Adjective, Full form, Nominative, Singular, Masculine
AFAP Adjective, Full form, Accusative, Plural // No gender in
Plural
ABSM Adjective, Brief form, Singular, Masculine //
ABAP Adjective, Brief form, Plural // No gender in
Plural
AC Adjective, Comparison form
VF Verb Infinitive
VIP1S Verb, Indicitive, Present/Future, 1 person, Singular
VITSM Verb, Indicitive, Past, Singular, Masculine
VM2S Verb, Imperative, 2 person, Singular
EXAMPLE INPUT FILE FORMAT
(Note
that the input word can have any form)
стекло
NNUNS
стол
NMUNS
стол
NMUGS
стол
NMUDS
стол
NMUPS
столами
NMUNS
столами
NMUGS
столами
NMUDS
столами
NMUPS
делал
VF
делаю
VIP1S
делать
VITSM
делаем
VM2S
OUTPUT FILE
стекло/
стол/
стола/
столу/
столе/
стол/
стола/
столу/
столе/
быстрые/быстрых/
делать/
делаю/
делал/
делаем/
There are two forms of an adjective, because one is animated and the
other is not.
Go to the personal page of Grigori Sidorov.
Go to the personal page of Alexander
Gelbukh.