Journal Article

CreoleVal: Multilingual Multitask Benchmarks for Creoles

Grobol, Loïc, Zhou, Li, Bollmann, Marcel, Ploeger, Esther, Armstrong, Ruth-Ann, Lhoneux, Miryam de, Lent, Heather, Belony, Paul, Chen, Yiyi, Hershcovich, Daniel, Heje, Hans Erik, Lavrinovics, Ernests, Dabre, Raj, DeGraff, Michel, Malau, Catriona, Bjerva, Johannes, Fekete, Marcell, Søgaard, Anders, Tatariya, Kushal, Eijansantos, Abee, Kanojia, Diptesh

2024

Overview

Creoles represent an under-explored and marginalized group of languages, with few available resources for NLP research. While the genealogical ties between Creoles and a number of highly resourced languages imply a significant potential for transfer learning, this potential is hampered due to this lack of annotated data. In this work we present , a collection of benchmark datasets spanning 8 different NLP tasks, covering up to 28 Creole languages; it is an aggregate of novel development datasets for reading comprehension relation classification, and machine translation for Creoles, in addition to a practical gateway to a handful of preexisting benchmarks. For each benchmark, we conduct baseline experiments in a zero-shot setting in order to further ascertain the capabilities and limitations of transfer learning for Creoles. Ultimately, we see as an opportunity to empower research on Creoles in NLP and computational linguistics, and in general, a step towards more equitable language technology around the globe.

• Publisher: MIT Press,The MIT Press
• Subject: Artificial Intelligence / benchmark / Computation and Language / Computer Science / Creole languages / dataset / natural language processing