Measuring HLT Research Equality of European Languages

Gorka Artola, German Rigau


Abstract
This work explores quantitative indicators that could potentially measure the equality and inequality research levels among the languages of the European Union in the field of human language technologies (HLT research equality). Our ultimate goal is to investigate European language equality in HLT research considering the number of papers published on several HLT research venues that mention each language with respect to their estimated number of speakers. This way, inequalities affecting HLT research in Europe will depend on other factors such as history, political status, GDP, level of social or technological development, etc. We have identified several groups of EU languages in the proposed measurement of HLT research equality, each group comprising languages with large differences in the number of speakers. We have discovered a relative equality among surprisingly different languages in terms of number of speakers and also relevant inequalities within the most spoken languages. All data and code will be released upon acceptance.
Anthology ID:
2022.tdle-1.4
Volume:
Proceedings of the Workshop Towards Digital Language Equality within the 13th Language Resources and Evaluation Conference
Month:
June
Year:
2022
Address:
Marseille, France
Venue:
TDLE
SIG:
Publisher:
European Language Resources Association
Note:
Pages:
36–45
Language:
URL:
https://aclanthology.org/2022.tdle-1.4
DOI:
Bibkey:
Cite (ACL):
Gorka Artola and German Rigau. 2022. Measuring HLT Research Equality of European Languages. In Proceedings of the Workshop Towards Digital Language Equality within the 13th Language Resources and Evaluation Conference, pages 36–45, Marseille, France. European Language Resources Association.
Cite (Informal):
Measuring HLT Research Equality of European Languages (Artola & Rigau, TDLE 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2022.tdle-1.4.pdf