All computer programs created by the CLL's staff and described on this site are distributed as freeware. Most of them can be downloaded from this site and from Yandex cloud storage where the files are checked for viruses.
The CLL offers the following linguistic software for download.
A Russian part-of-speech tagger designed as a module of an opinion mining system.
Y-stemmer (Yatsko's stemmer) - a stemmer built on preliminary POS-tagging that outperforms existing analogues.
Download YAVA-STEMMER, a hybrid advanced user-focused Russian stemmer:
CLL-tagger - a part-of-speech probabilistic tagger that works faster than existing analogues providing the same quality.
Download CLL tagger:
UNIS (Universal summarizer) performs adaptive text summarization.
Linguistic Toolbox (LIT) is a concordancer that allows creating POS-annotated corpora and perform all types of searches adoped in corpus linguistics.
To start LIT double click LToolBoxGUI.exe file in program's directory.
Download Linguistic Toolbox:
Linguistic Toolbox Extended can perforn addtional operations of union, substruction, and intersection.
Download Linguistic Toolbox Extended:
User Guide.doc file is in program's directory.
TF*IDF Ranker performs term weighting according to the well-known formula and its modification suggested by V.Yatsko. TfIDF Ranker_2L supports English and Russian.
Download English version
Download English and Russian version of TFIDF Ranker
Compare performs calculations according to Swadesh's formula.
PASS - Partially Automated Symmetric Summarization, a network computer system for TEFL.
Download PASS Demo:
TITE - Translation in Teaching English, a network computer system for TEFL
Y-Mining - an intelligent opinion mining system. Feel free to use sample texts include into the archive to test the system.
Y-Structurer - an application that helps to create a graphic representation of text structure.
Download Text Structurer:
Y-Sets - an application for statistical text processing. It allows the user to get statistics about identical words in a number of texts performing the intersection procedure. The user can also obtain statistics about the words that occur in a specific text/texts and don't appear in the other texts under analysis.