Difference between revisions of "Lexicon extraction software"
Jump to navigation
Jump to search
m |
|||
Line 1: | Line 1: | ||
Software for extracting monolingual or bilingual [[lexicon]]s from [[corpora]]. Either fully-automated or partially-automated. | Software for extracting monolingual or bilingual [[lexicon]]s from [[corpora]]. Either fully-automated or partially-automated. | ||
+ | |||
+ | ==Free software== | ||
* [http://www.cs.chalmers.se/~markus/extract/ Extract tool] - Developed by Markus Forsberg and Aarne Ranta. Written in Haskell, matches lemmas to paradigms based on [[regular expression]]s. | * [http://www.cs.chalmers.se/~markus/extract/ Extract tool] - Developed by Markus Forsberg and Aarne Ranta. Written in Haskell, matches lemmas to paradigms based on [[regular expression]]s. | ||
+ | |||
+ | ==Proprietary== | ||
*[http://similis.fr/NewLM/ExTermino/index.php?lang=en ExTermino] - fully automated web-based terminology extraction built from [http://lingua-et-machina.com/ Similis], the 2nd generation Translation Memory using chunk analyzes technology. | *[http://similis.fr/NewLM/ExTermino/index.php?lang=en ExTermino] - fully automated web-based terminology extraction built from [http://lingua-et-machina.com/ Similis], the 2nd generation Translation Memory using chunk analyzes technology. | ||
[[Category:Lexicon extraction software|*]] | [[Category:Lexicon extraction software|*]] |
Revision as of 02:01, 1 February 2007
Software for extracting monolingual or bilingual lexicons from corpora. Either fully-automated or partially-automated.
Free software
- Extract tool - Developed by Markus Forsberg and Aarne Ranta. Written in Haskell, matches lemmas to paradigms based on regular expressions.