18.2060, FYI: ELRA - Catalog Update

[LINGUIST Network]

LINGUIST List: Vol-18-2060. Mon Jul 09 2007. ISSN: 1068 - 4875.

Subject: 18.2060, FYI: ELRA - Catalog Update

Moderators: Anthony Aristar, Eastern Michigan U <aristar at linguistlist.org>
            Helen Aristar-Dry, Eastern Michigan U <hdry at linguistlist.org>
 
Reviews: Randall Eggert, U of Utah  
         <reviews at linguistlist.org> 

Homepage: http://linguistlist.org/

The LINGUIST List is funded by Eastern Michigan University, 
and donations from subscribers and publishers.

Editor for this issue: Fatemeh Abdollahi <fatemeh at linguistlist.org>
================================================================  

To post to LINGUIST, use our convenient web form at
http://linguistlist.org/LL/posttolinguist.html.

===========================Directory==============================  

1)
Date: 09-Jul-2007
From: Helene Mazo < mazo at elda.org >
Subject: ELRA - Catalog Update

 

	
-------------------------Message 1 ---------------------------------- 
Date: Mon, 09 Jul 2007 09:56:09
From: Helene Mazo < mazo at elda.org >
Subject: ELRA - Catalog Update 
 


The Evaluation Packages resulting from the following projects: ARCADE II,
CESART, CESTA, ESTER, EQueR, EvaSy and MEDIA, are now available in the ELRA
Catalogue of Language Resources (http://catalog.elra.info/).

These Evaluation Packages were produced within the French national research
programme Technolangue funded by the French Ministry of Research and New
Technologies (MRNT). Each package includes the material that was used
and/or produced for each evaluation campaign: resources, protocols and
metrics, scoring tools, results of the campaign, etc. The aim of these
evaluation packages is to enable external players to evaluate their own
system and compare their results against the state of the art.

The technologies that could be evaluated within this programme are as follows:
-	Speech Technologies:
-	Speech synthesis:
The EvaSy project enabled to carry out a campaign for the evaluation of
speech synthesis systems using French text data. Three actions were
considered during the campaign: evaluation of grapheme-to-phoneme
conversion, evaluation of prosody, global evaluation of the quality of
speech synthesis systems.

 For details on the EvaSy Evaluation Package, see:
 ELRA-E0023
-	Transcription of Broadcast News:
The ESTER project enabled to carry out a campaign for the evaluation of
speech recognition systems that produce Broadcast News enriched
transcription for French. Three actions were considered during the
campaign: orthographic transcription, segmentation and information
extraction (named entity tracking). For details on the ESTER Evaluation
Package, see:  ELRA-E0021. For research or commercial use of this database,
please refer to ELRA-S0241 ESTER Corpus. 
-	Speech Dialogue (for tourist information-oriented servers):
The MEDIA project enables to carry out a campaign for the evaluation of
man-machine dialogue systems for French. The campaign is distributed over
two actions: an evaluation taking into account the dialogue context and an
evaluation not taking into account the dialogue context. For details on the
MEDIA Evaluation Package, see:  ELRA-E0024 
-	Written Technologies : 
-	Alignment of Multilingual Corpora:
The ARCADE II project enables to carry out a campaign for the evaluation in
the field of multilingual alignment. Two actions were considered during the
campaign: sentence alignment and translation of named entities. For details
on the ARCADE II Evaluation Package, see:  ELRA-E0018 
-	Machine Translation:
The CESTA project enabled to carry out a campaign for the evaluation of
machine translation technologies. Two actions were considered during the
campaign: evaluation on a general vocabulary and evaluation on a specialty
domain (evaluation after terminology enrichment). For details on the CESTA
Evaluation Package, see:  ELRA-E0020 
-	Acquisition of Terminological Resources:
The CESART project enabled to carry out a campaign for the evaluation of
tools for the acquisition of terminological resources. Two actions were
considered during the campaign: term extraction and extraction of relations
between terms within text data. For details on the CESART Evaluation
Package, see:  ELRA-E0019 
-	Question-Answering Task for Information Retrieval:
The EQueR project enabled to carry out a campaign for the evaluation of
Question-Answering systems in French. Two actions were considered during
the campaign: one generic task and one specialized task (medical domain).
For details on the EQueR Evaluation Package, see:  ELRA-E0022 
-	Syntactic Parsers:
The EASy project enabled to carry out a campaign for the evaluation of
syntactic parsers. Two actions were considered during the campaign:
annotation within constituents and annotation between dependency relations. 
Evaluation Package to be published soon.
ELRA takes the opportunity of this announcement to thank all scientific
coordinators and participants who made this work possible.

More information on the ELRA catalogue, please contact Valérie Mapelli
(mailto:mapelli at elda.org) 



Linguistic Field(s): Computational Linguistics





 





-----------------------------------------------------------
LINGUIST List: Vol-18-2060