[Corpora-List] Temporal Tagger HeidelTime supporting 7 languages now

[Jannik Strötgen]

Dear all,

We are happy to announce a new stable version 1.4 of HeidelTime 
(https://code.google.com/p/heideltime).

The new version supports temporal tagging of seven languages, including 
Arabic and Vietnamese for which HeidelTime is now the first publicly 
available temporal tagger performing the full task of temporal tagging, 
i.e., the extraction and the normalization of temporal expressions. For 
the normalization of temporal expressions in all languages, different 
normalization strategies are applied depending on the document type. In 
particular, HeidelTime distinguishes between news-style and 
narrative-style documents (such as Wikipedia articles).

At this year's TempEval-3, HeidelTime achieved the best results for the 
task of temporal tagging (extraction+normalization) for English and Spanish.

HeidelTime is available as UIMA-component and as standalone version. 
Additional information, download links, and evaluation results can be 
found on:
http://code.google.com/p/heideltime/

An online demo is also available:
http://heideltime.ifi.uni-heidelberg.de/heideltime/

Your feedback is highly appreciated.

Best regards,
The HeidelTime Team
https://code.google.com/p/heideltime
Twitter: @HeidelTime


-- 
Jannik Strötgen
Institute of Computer Science
Im Neuenheimer Feld 348
69120 Heidelberg
Germany
Phone: +49 (0) 6221 / 54-5709
eMail: stroetgen at uni-hd.de



_______________________________________________
UNSUBSCRIBE from this page: http://mailman.uib.no/options/corpora
Corpora mailing list
Corpora at uib.no
http://mailman.uib.no/listinfo/corpora