Skip to main content

5.1.25.1. Spain / Basque

FLaReNet Summary

There is presently no big national/regional program for Basque. The most important initiative to mention is that among the ~25 research lines in the ETORTEK R+D calls published by the Basque Government, one of those lines is related to Language technology (Anhitz2005-2008 project and Hizking2002-2005 project).

Information about Language Resources in Basque may be found on the IXA Webpage: ACL wiki. Resources_for_Basque, and comprise several Research Groups: AHOLAB: Speech Processing for Basque, University of Alicante (GPLSI: Research Group of Language Processing and Information Systems) and Transducens. University of Alicante, for Machine Translation. There are many collaborating Companies: Code&Syntax, Diana Teknologia, Eleka Linguistic Engineering, Elhuyar, Euskaldun Egunkaria newspaper, Hizkia, imaxin|software, Irion Technologies, Plazagunea, Thera, Centre de Llenguatges i Computació, S.L., UZEI, Prompsit, VICOMTech …

A PhD program on the Analysis and processing of Language is organized by five departments from the University of the Basque Country with collaboration of UEU (Summer Basque University).

Inguma is a database of the Basque scientific-intellectual community, where to find Basic information about all the Written or Spoken Language Resources produced in Basque in the different areas of knowledge.

Contact Point Input

National/Regional contact: Kepa Sarasola, Ixa Group, University of the Basque Country.

Programs

There is presently no big national/regional program for Basque. The most important initiative to mention is that among the ~25 research lines in the ETORTEK R+D calls published by the Basque Government[1], one of those lines is related to Language technology (see Anhitz2005-2008 project, and Hizking2002-2005 project).

Information about Language Resources in Basque may be found at the IXA Webpage: ACL wiki. Resources_for_Basque, and comprise:

Euskalbar
A Firefox plugging to simultaneously make queries to many on-line dictionaries in Basque, Spanish, French and English.

hiztegia.net
Links to more than 50 electronic dictionaries of Basque.

General registry of Software in Basque
The section related to language applications in Softkat, a general catalog of software products adapted or created for their usage in Basque (just in Basque).

Inventory of Basque IST
The Department of Language Politics of the Basque Government compiled in 2006 this inventory of IST products, agents and projects related to Basque (it is not updated).

General description of Basque and some tools
It is included in the Basque Government's web. The following tools for Basque can be downloaded: the spelling checker for Basque, a document database system, and the Panda Titanium antivirus. Some Basque dictionaries and a terminological database can be consulted.

Elhuyar Language Services
The Language Service of Elhuyar Foundation. Dictionary search, Science and Technology Corpus, CorpEus (Web as a corpus), Itzulterm (terminological data-base), Opentrad (Machine Translation system) and Elebila (Web searching for contents in Basque).

AHOLAB: Speech Processing for Basque
There is a very good TTS system that reads text in Basque: Nuance, TTS for Basque.

NLP resources:

ACL wiki. List_of_resources_by_language

TIMM: Red Temática en Tratamiento de la Información Multilingüe y Multimodal

Know2 project: inventory of linguistic processing resources and tools

Products created by IXA group

Clarin Basque (59)
http://www.clarin.eu/vlo/index.php?page=facetted-browsing&sub=0

Genre
Written Corpus (2)
Lexicon / Knowledge Source (2)
Terminological Resource (1)
Treebank (1)

Subject (group results)
typology (29)
generalinguistics (29)
syntax (21)
language_description (14)
morphology (12)
semantics (9)
phonetics (6)
phonology (6)
lexicon (2)
discourse_analysis (1)

Research Groups

AHOLAB: Speech Processing for Basque

University of Alicante (GPLSI: Research Group of Language Processing and Information Systems)

Transducens. University of Alicante
Machine Translation

Collaborating Companies

Code&Syntax
This company is dedicated to making the Internet a truly global experience through internationalization and localization services.

Diana Teknologia
Information management and communication for companies.

Eleka Linguistic Engineering
It provides R+D+I solutions to companies and entities focused on the knowledge management and the application of Information Technologies.

Elhuyar
R&D company related with Basque Processing.

Euskaldun Egunkaria newspaper
This newspaper collaborates with the IXA Group building text corpora. It uses tools developed by IXA.

Hizkia
Company related with Basque Processing. Hizkia collaborates with the IXA Group in a spelling checker development.

imaxin|software
Working on both Galician and Language Technology.

Irion Technologies
Irion Technologies is a company that develops intelligent software to improve the quality of retrieval for everybody who uses the web.

Plazagunea
It collaborates with IXA Group in the development of a lemmatization-based web-crawler.

Thera, Centre de Llenguatges i Computació, S.L.
Working on Catalan, Spanish and Language Technology.

UZEI
This institute has collaborated with the Ixa Group in many projects (Spelling Checker, Lexical Database ...).

Prompsit
This group collaborates with the IXA group in developing the machine translation systems in the OpenTrad platform (Spanish-Catalan, Spanish-Galician, Spanish-Basque). They developed the MT systems interNOSTRUM (Spanish-Catalan), and Traductor Universia (Spanish-Portuguese).

VICOMTech
An applied research centre working in the area of interactive computer graphics and digital multimedia. Between the main research activities of VICOMTech are in interactive digital television, multi-lingual conversational interfaces based upon 3D Avatars for education, entertainment, and on-line information services.

Others

Analysis and processing of Language
PhD program organized by five departments from the University of the Basque Country with collaboration of UEU (Summer Basque University). Broad participation of the IXA Group.

Inguma: a database of the Basque scientific-intellectual community
Basic information about all the Written or Spoken Language Resources produced in Basque in the different areas of knowledge.

Many activities are on-going on the processing of the Basque language, such as:

A Summer course on "Language managing in the global world / Hizkuntzen kudeaketa mundu global batean" (30 hours, in Basque, September 1-3, 2010), included in the XXIX Summer School of the University of The Basque country Donostia-San Sebastián;

Registration for the Master on "Analysis and Processing of Language / Hizkuntzaren Azterketa eta Prozesamendua" in September 2010;

Local seminar in November on "Collaborative Language Engineering" organized by the IXA group, OpenMT-2 project and eu.wikipedia community (working on the enrichment of the Wikipedia in Basque). It will be studied how collaborative communities, specially Wikipedia, can help in NLP and MT in particular.

 


[1] Director of language politics: Lourdes Auzmendi; Coordinator of language politics: Araceli Díaz de Lezana (a-lezana@ej-gv.es).