26.1045, Calls: Computational Linguistics/France

Tue Feb 24 04:35:40 UTC 2015

LINGUIST List: Vol-26-1045. Mon Feb 23 2015. ISSN: 1069 - 4875.

Subject: 26.1045, Calls: Computational Linguistics/France

Moderators: linguist at linguistlist.org (Damir Cavar, Malgorzata E. Cavar)
Reviews: reviews at linguistlist.org (Anthony Aristar, Helen Aristar-Dry, Sara Couture)
Homepage: http://linguistlist.org

Editor for this issue: Erin Arnold <earnold at linguistlist.org>
================================================================

Date: Mon, 23 Feb 2015 23:34:58
From: Marianne Vergez-Couret [vergez at univ-tlse2.fr]
Subject: Natural Language Processing for French and European Regional Languages

Full Title: Natural Language Processing for French and European Regional Languages 
Short Title: TALaRE 2015 

Date: 22-Jun-2015 - 22-Jun-2015
Location: Caen, France 
Contact Person: Marianne Vergez-Couret
Meeting Email: vergez at univ-tlse2.fr

Linguistic Field(s): Computational Linguistics 

Call Deadline: 04-Apr-2015 

Meeting Description:

Held in conjunction with TALN 2015 (22e conférence sur le Traitement Automatique des Langues Naturelles, Caen, France, June, 22-25 2013)

Research in natural language processing for under-resourced languages is currently an active area, in a global perspective of cultural heritage preservation. Regional languages generally fall into this category, as electronic resources for these languages are rare and sometimes non-existent. Providing electronic resources for these languages (including written corpora, lexicons and dictionaries) is a major asset for supporting their dissemination, teaching, preservation or standardization. It is, among others, necessary to develop written corpora, which are the most representative of language use, by collecting written works of various genres (literature, theater, poetry, storytelling, press ...) and, for some languages, by taking variation into account (dialectal, phonological or graphical variations). The second step is logically to enrich the corpora with annotations. The development of annotated corpora for regional languages raises many methodological issues. It is not always po
 ssible to directly transpose existing models for resource-rich languages, partly because of dialectal and phonological variation and the lack of writing standards. The corpora are also a basis for the development of dictionaries, lexicons and glossaries and are necessary for the description of the actual use of a language. On the other hand, dictionaries and lexicons are needed to support the development of the corpora (optical character recognition, lemmatization and morpho-syntactic analysis). When these resources already exist for a language (dictionaries, lexicons, bilingual glossaries coupling a regional and a national language), the question arises as to how information contained in these resources can be shared and possibly be enriched with additional annotations (phonetic, morphosyntactic, syntactic, ...). Finally, corpora and lexicons are necessary for the development of natural language processing tools (morpho-syntactic analysis or syntactic analyzers ...).

Beyond the technical and methodological challenges, the more pragmatic difficulties related to the lack of financial and human resources to carry out the creation of resources should not be neglected. This workshop aims to bring together researchers involved in the creation of language resources and ''basic'' NLP tools for French and European regional languages, in order to share their views, methodologies and techniques.

Call for Papers:

We invite submission of papers on the constitution of resources and tools for regional or minority languages of France and Europe (including languages from overseas departments and territories of France). Submissions may concern completed work or preliminary studies. 

Topics of interest include, but are not limited to:

- Resources: Written corpus building; Development of lexicons, dictionaries, glossaries
- Tools: Scanning, OCR and text encoding; Linguistic annotations (manual and automatic for morpho-syntactic or syntactic analysis,...); Corpus management and query
- Articulation between theory and practice when dealing with variation
- Road maps for resources and tools

Paper Submission:

Papers will be written in French for French-speaking authors or English for non-French-speaking authors. They should have up to 12 pages in the TALN 2015 format for long papers, or up to 6 pages for short papers.  A LaTeX style file and a MS Word and OpenOffice template are available on the conference website (https://taln2015.greyc.fr/soumissionstaln/). Accepted papers will be presented during the workshop.

Authors should submit the papers in PDF through the submission page at
https://easychair.org/conferences/?conf=talare2015

Selection Criteria:

The selection criteria will be the same as those that apply for TALN 2015 research articles.

Important Dates:

- Paper submission deadline: April 5, 2015
- Notification of paper acceptance: May 4, 2015
- Deadline for camera-ready versions: May 22, 2015

----------------------------------------------------------
LINGUIST List: Vol-26-1045	
----------------------------------------------------------