PT
UniDive – Universality, diversity and idiosyncrasy in language technology
Identification
- Project identification: Universality, diversity and idiosyncrasy in language technology (UniDive) [COST Action 21167]
- Coordination: Agata Savary (Université Paris-Saclay)
- Responsible at CLUNL: Raquel Amaro (Lexicology, Lexicography and Terminology group)
- Duration: Sep. 2022 – Sep. 2026
- Funding entity: European Science Foundation
- Keywords: natural language processing; language universals; diversity; idiosyncrasy; language resources and tools
- Website: https://www.cost.eu/actions/CA21167/
Description
The UniDive Action takes two original stands on this challenge. Firstly, it aims at embracing both inter- and intra-language diversity, i.e. a diversity understood both in terms of the differences among the existing languages and of the variety of linguistic phenomena exhibited within a language. Secondly, UniDive does not assume that linguistic diversity is to be protected against technological progress but strives for both of these aims jointly, to their mutual benefit. Its approach is to: (i) pursue NLP-applicable universality of terminologies and methodologies, (ii) quantify inter- and intra-linguistic diversity, (iii) boost and coordinate universality- and diversity-driven development of language resources and tools. UniDive builds upon previous experience of European networks and projects which provided a proof of concept for language modelling and processing, unified across many languages but preserving their diversity. The main benefits of the Action will include, on the theoretical side, a better understanding of language universals, and on the practical side, language resources and tools covering, in a unified framework, a bigger variety of language phenomena in a large number of languages, including low-resourced and endangered ones.
(Retrieved from the COST Action website)
Participating entities
Full information at:
https://www.cost.eu/actions/CA21167/#tabs+Name:Working%20Groups%20and%20Membership
Menu < back
- Projects
- Ongoing projects
- MultiPoD – Multilingual and Multicultural Spaces for Political Deliberation
- HEREDITARY – HetERogeneous sEmantic Data Integration for guT-brAin interplay
- TTC-CPLP – Terminologias Técnicas e Científicas para a CPLP
- CHAMUÇA – Portuguese and South Asian Lexicon Archive
- e-Term ANCV – Recurso terminológico jurídico-parlamentar digital Assembleia Nacional de Cabo Verde
- NObarriers2Health: Reducing language and cultural barriers through machine translation literacy for inclusive multilingual health communication
- EPISTRAN – Epistemic Translation: Towards an Ecology of Knowledges
- DiTo – Didática do Texto
- REDGRAM – Digital Resources for Education – Grammatical Pathways
- iRead4Skills – Intelligent Reading Improvement System for Fundamental and Transversal Skills Development
- Active Citizenship Through Dialogue in Virtual teacher communities
- ProPerL2 – Production and Perception in L2 speech learning
- Heritage Languages go to School: The interplay of (extra)linguistic factors in successful language development
- Investigating the impact of implicit and explicit instruction on phonological acquisition in a second language
- LAUA – Language Attrition and Ultimate Attainment
- CORRELATE – Corpora and Lexical and Terminological Resources
- ANACOREX – Anafora y expresiones referenciales en el bilinguismo: triangulando enfoques de corpus y experimentales
- Caring Communication: gene therapy in the context of hemophilia
- CoRaLHis – Comparing Romance Languages through History: building a multilingual parallel diachronic corpus (13th-18th C.)
- MorDigital – Digitisation of Diccionario da Lingua Portugueza by António de Morais Silva
- EXPRIMI
- Language and literacy at school – the contribution of metasyntactic abilities to reading comprehension development
- G&T.Comenta
- COVID-19 Collaborative Glossary
- TERMVEST – The Clothing Terminology: European Portuguese version
- Digital Edition of the “Vocabulário Ortográfico da Língua Portuguesa” (VOLP-1940)
- PIPALE – Preventive Intervention Project for Learning to Read and Write
- POR Nível – Design and validation of a placement test to PFL
- Cultural Heritage Lexicon
- Concluded projects
- Western Sephardic Diaspora Roadmap
- ELEXIS – European Lexicographic Infrastructure
- Humanities Going Digital (HUGOD)
- LL2DS – Linking Linguistics to Data Science
- QuILL – Quality in Language Learning
- Corpus Linguístico & Avatar para a Língua Gestual Portuguesa
- Monitor Corpora. PressCoronaVírus
- Com@Rehab – Communication for interactive rehabilitation in virtual reality
- Read4Succeed: Improving migrant, refugee and from deprived neighbourhood children reading skills through an Animal Assisted Reading program
- Project GiroFLE
- ANACOR: A corpus-based approach to anaphora resolution in second language acquisition: beyond the interfaces
- OrthoDef
- European Portuguese-Standard Arab Dictionary
- MOCOLANG-O – MOdélisation COnceptuelle des troubles (du LANGage et de la communication) en Orthophonie
- Romance clitics in diachrony. An integrated approach
- Portuguese Literature Corpus for Distant Reading
- ALPROF – Automatic Assessment of Language Proficiency for Migrant Integration
- CLARIN CLUNL
- Utopia, Food and the Future
- Development of syntactic structures in Portuguese and French monolingual and bilingual acquisition
- The Case of Grammatical Relations
- BlackBox – a Collaborative Platform to Document Performance Composition: from conceptual structures in the backstage to customizable visualizations in the front-end
- Promotion of scientific literacy
- PerGRam – Percursos para o ensino da gramática nos primeiros anos de escolaridade
- Knowledge Organisation Proposal within the scope of infertility: the role of Terminology
- Subordination in Medieval Portuguese
- Crosslinguistic and Crosspopulation approaches to the Acquisition of Dependencies
- Syntactic and lexical factors in processing complexity
- SIERA – Integrating Sina Institute into the European Research Area
- Syntactic Dependencies from 3 to 10
- Events and subevents in Capeverdean
- TKB – Transmedia Knowledge Base for Contemporary Dance
- Research network projects
- ELEXIS Association
- PhraConRep – A Multilingual Repository of Phraseme Constructions in Central and Eastern European Languages
- Y-JustLang – Justice to youth language needs
- ENEOLI – European Network On Lexical Innovation
- Consortium Huma-Num ARIANE
- GRAFE’Maire
- UniDive – Universality, diversity and idiosyncrasy in language technology
- Metalex – International Metalexicography Network
- @ Cientista Regressa à Escola
- CLIL in Languages Other Than English
- NexusLinguarum – European network for Web-centred linguistic data science
- Distant Reading for European Literary History
- HL2C – Heritage Language Consortium
- KEYSTONE – Semantic Keyword-Based Search on Structures Data Sources
- ARLE – International Association for Research in L1 Education
- ENeL – European Network of e-Lexicography
- GraMaLL – Grasping Meaning Across Languages and Learners
- Language Impairment in a Multilingual Society: Linguistic Patterns and the Road to Assessment
- GIRTraduvino – Grupo de Investigación Reconocido sobre la Lengua de la Vid Y el Vino y su Traducción
- Value for Health CoLAB
- Infrastructures
- Services provision