Termout.org logo/LING

Update: February 22, 2022
There is now some form of information extraction. We are mining definitions and bibliographic references. (e.g. http://tecling.com/cgi-bin/termout/ling/index.pl?input=écfrasis ).

Update: February 21, 2022

10001 entries

We have now aligned the terms in both languages. Not all of them but quite a few, and the quality of the alignment seems decent. Next step will be semantic categorization, term-variation identification and information extraction.

Back to home page

Update: February 8, 2022
The terms have been separated by language and lemmatized.
Semantic classification and language alignment are pending tasks.

First version: January 31, 2022
We are presenting yet another new project. It's about a version (currently in development) of our terminology extraction program termout.org that now can be applied to specific domains and corpora, with far better results. The version currently available on the web site termout.org is agnostic to the domain, it's an ``all terrain'' version. The new version will probably be available here in the coming days. But for the moment, we have a nice example of what it can do: this website offers a full list of thousands of linguistic vocabulary forms in Spanish and English.
This time you can help: the website allows you to flag a term candidate if you think it is a false positive (there's quite a few of those).