[Corpora-List] EVALITA 2009 Second Call for Participation

Manuela Speranza manspera
Tue Apr 21 14:14:55 CEST 2009

<apologies for cross-posting>



Evaluation of NLP and Speech Tools for Italian



EVALITA 2009 - Second Call for Participation April 2009

We are pleased to announce that the development data for the different tasks of EVALITA 2009 are now available. We take this opportunity to launch a second call for participation. The general objective of EVALITA is to promote the development of language technologies for the Italian language, providing a shared framework where different systems and approaches can be evaluated in a consistent manner.

We invite participation, both from academic institutions and industrial organizations, in eight tasks, all for Italian. With respect to the previous edition, tasks also include a range of Speech tasks and a new Textual Entailment task.

Text tasks - PoS-Tagging - Parsing

- Dependency Parsing

- Constituency Parsing - Lexical substitution - Entity Recognition

- Named Entity Recognition

- Local Entity Detection and Recognition - Textual Entailment

Speech tasks - Connected Digits Recognition

- Clean Digits

- Noisy Digits - Dialogue System Evaluation - Speaker Identity Verification

- Application

- Forensic

As with the previous edition, guidelines describing the different tasks are available for download from the EVALITA website. Participants will also be provided with training data and will have the chance to test their systems with the evaluation metrics and procedures to be used in the formal evaluation. The results of the evaluation will be disseminated at the final workshop, which will be organized in conjunction with AI*IA 2009 and will take place in Reggio Emilia on December 12th, 2009.

In order to register for one or more of the EVALITA 2009 tasks, please go to the registration page of the EVALITA 2009 website: http://evalita.fbk.eu/registration.html

For more detailed information please refer to the website at http://evalita.fbk.eu


- 1st February 2009: on-line registration opens - 1st April 2009: development data available to participants - 10th September 2009: test data available, registration closes - 20th September 2009: system results due to organizers - 5th October 2009: assessment returned to participants - 25th October 2009: technical reports due to organizers - 12th December 2009: final workshop, Reggio Emilia

Coordination: Bernardo Magnini (FBK-irst) and Amedeo Cappelli (ISTI-CNR and CELCT)

Task Organization: - PoS-Tagging: Giuseppe Attardi and Maria Simi (Uni. Pisa) - Parsing: Cristina Bosco, Alessandro Mazzei, Vincenzo Lombardo (Uni. Torino), Felice dell'Orletta, Alessandro Lenci (Uni. Pisa) and Simonetta Montemagni (ILC-CNR, Pisa) - Lexical Substitution: Antonio Toral (ILC-CNR, Pisa) - Entity Recognition: Manuela Speranza (FBK-irst, Trento), Valentina Bartalesi Lenzi and Rachele Sprugnoli (CELCT, Trento) - Textual Entailment: Johan Bos (Uni. Roma "La Sapienza"), Marco Pennacchiotti (Saarland University) and Fabio Massimo Zanzotto (Uni. Roma "Tor Vergata") - Connected Digits Recognition: Gianpaolo Coro (ABLA, Milano), Roberto Gretter and Marco Matassoni (FBK-irst, Trento) - Spoken Dialogue Evaluation: Giuseppe Riccardi (Uni. Trento), Francesco Cutugno (Uni. Napoli "Federico II"), Roberto Pieraccini (Speechcycle, New York) and Morena Danieli (Loquendo, Torino) - Speaker Identity Verification: Guido Aversano (Parrot SA, Paris) and Luciano Romito (Uni. Calabria, Cosenza)

Contact: Manuela Speranza - manspera at fbk.eu

More information about the Corpora mailing list