Take a look at the private site...
Scheme
- Scheme Snippets R6RS
- course material for ESSLLI 2006
- the Scheme Natural Language Toolkit (version 0.1 includes stop-word lists for various languages, stemmer, chart parser, frequency table generation, n-gram model generation etc.) (as PLT-Scheme modules and R6RS libs)
see Scheme Snippets for that...
- course material for ESSLLI 2006
- the Scheme Natural Language Toolkit (version 0.1 includes stop-word lists for various languages, stemmer, chart parser, frequency table generation, n-gram model generation etc.) (as PLT-Scheme modules and R6RS libs)
see Scheme Snippets for that...
Python
- course material
for JSSECL
2006
- course material for the DGfS/CL Fall School 2005
- Corpus processing tools (TEI XML from HTML, XML filtering, quantitative analysis)
- Language identification (LID) with n-gram models
- Orthography to IPA conversion for Croatian
- Chart parsing (Charty)
- Finite State Automata (FSA) scripts: FSA class, automaton from word list, DOT (Graphviz) from automaton
- course material for the DGfS/CL Fall School 2005
- Corpus processing tools (TEI XML from HTML, XML filtering, quantitative analysis)
- Language identification (LID) with n-gram models
- Orthography to IPA conversion for Croatian
- Chart parsing (Charty)
- Finite State Automata (FSA) scripts: FSA class, automaton from word list, DOT (Graphviz) from automaton
Java
- Guessing Chart Parser with mini-grammars for English and
Croatian
- Regular Expression and Grammar Toolkit
- Regular Expression and Grammar Toolkit
C++
- Ragel-based morphology analysis for Croatian
Mac OS X tools
- conversion from Apple
Mail 2 (and 3) to Thunderbird/Evolution/KMail (Python source/html) (there is a basic GUI in Tkinter, should be OK
for basic conversion, converts into Thunderbird folder structures, just copy the
resulting folder into your Thunderbird Local Mail folder)
Other stuff
CroMo - a FSA-based high-performance morphological
parser, annotator and lemmatizer for Croatian
- Alignment Based Unsupervised Grammar Induction (ABUGI) code in Python, Scheme, and Objective-C, for morphology only... so far...
- Alignment Based Unsupervised Grammar Induction (ABUGI) code in Python, Scheme, and Objective-C, for morphology only... so far...
