 |
|
Acquisition and documentation of tools is just getting under way. See the
links page for more tools available elsewhere.
Draft standards for the documentation of software tools are now available at
the LJU1 TELRI page
at the Jozef Stefan Institute in Ljubljana, Slovenia.
Finite state utilities
Finite state utilities include two software packages Finite State automata (fsa) and
transducers (utr) that can be used for spellchecking, diacritic restoration, morphological analysis
and synthesis, acquisition of data for morphological descriptions, and perfect hashing.
Both packages are written in C++, and they can be compiled with g++.
Resource provider: Jan Daciuk, Technical University of Gdańsk, Poland.
Go to Finite state utilities
Contact details
Perl scripts for multilingual concordancing
Perl scripts for making and searching POS annotated multilingual concordances in
XML format.
Resource provider: Serge Sharoff, The Russian Research Institute for
Artificial Intelligence.
Go to Perl scripts
Entropizer 1.1
This software is developed for computing symbol entropy on raw
texts. It is designed
to run on Macintosh computers.
Resource provider: Aris Xanthos, University of Laussanne.
Contact details
Browse or
download Stuffit Lite archive.
Bigram Statistics Package (BSP)
This package supports the analysis of bigrams that appear in text using Fisher's
exact test, the log likelihood ratio, Pearson's chi-squared text, and the Dice
Coefficient. BSP is designed so that you can easily add your own statistics. BSP
is written by Ted Pedersen. Go to BSP.
Resource provider: Ted Pedersen.
Contact details
QWICK
QWICK for TRACTOR corpus analysis program, written by Oliver Mason,
Centre for Corpus Research, Department of English, University of Birmingham.
Go to Qwick.
Vanilla aligner
A program which performs automatic
sentence alignment of parallel texts.
This is an implementation of the Gale and Church (1993) algorithm.
Resource provider: Pernilla Danielsson and
Daniel Ridings at the University of Gothenburg.
Contact
details
Browse the files or
download everything.
PC-Kimmo
The pc-kimmo morphological analyzer and other tools (from Summer Institute of Linguistics).
Browse the files.
Contact
details
QTAG
QTAG is a portable and language-indepentdent part-of-speech tagger.
Browse the files
Contact
details
EVA
Combined editor, database, and tagger.
Browse the files.
Contact
details
Estonian Tagger
Estonian Morphological Analyzer.
Resource provider: Dept of Computer Science and Dept of General
Linguistics, University of Tartu, Tartu, Estonia.
Browse the files.
Contact
details
Email the Tractor helpdesk
for queries regarding accessing and depositing resources.
|