Technolangue/Easy

Technolangue/Easy

Technolangue/Easy was the first evaluation campaign for the syntactic parsers of French.

This project was supported by the French Research Ministry.

Technolangue/Easy included four tasks between 2003 and 2006:
* corpora constitution
* production of consensual annotation guidelines
* manual corpora annotation using a dedicated annotation formalism
* evaluation of the participating parsers

13 laboratories and companies submitted their parser to the evaluation (making a total of 16 runs) with 7 research laboratories, 3 R&D institutes and 3 private companies. Said in other terms, most of the existing French parsers competed.

External links

* [http://www.limsi.fr/RS2005/chm/lir/lir11/ protocol description (in English)]
* [http://www.technolangue.net/article198.html Technolangue/Easy web page (in French)]

References

* Gendner V., Illouz G., Jardino M., Monceaux P., Robba I. Vilnat A (2003) PEAS, the first instantiation of a comparative framework for evaluating parsers of French, Proceedings of the Research Note Sessions of the 10th Conference of the EACL, Budapest, Hungary
* Paroubek P., Robba I., Vilnat A., Ayache C. (2006) Data annotations and mesures in EASY, the evaluation campaign for parsers in French LREC, Genoa


Wikimedia Foundation. 2010.

Игры ⚽ Поможем сделать НИР

Look at other dictionaries:

  • Natural language processing — (NLP) is a field of computer science and linguistics concerned with the interactions between computers and human (natural) languages; it began as a branch of artificial intelligence.[1] In theory, natural language processing is a very attractive… …   Wikipedia

Share the article and excerpts

Direct link
Do a right-click on the link above
and select “Copy Link”