On Language Models for Creoles
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Standard
On Language Models for Creoles. / Lent, Heather; Bugliarello, Emanuele; De Lhoneux, Miryam; Qiu, Chen; Søgaard, Anders.
Proceedings of the 25th Conference on Computational Natural Language Learning. Association for Computational Linguistics, 2021. s. 58-71.Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - On Language Models for Creoles
AU - Lent, Heather
AU - Bugliarello, Emanuele
AU - De Lhoneux, Miryam
AU - Qiu, Chen
AU - Søgaard, Anders
PY - 2021
Y1 - 2021
N2 - Creole languages such as Nigerian Pidgin English and Haitian Creole are under-resourced and largely ignored in the NLP literature. Creoles typically result from the fusion of a foreign language with multiple local languages, and what grammatical and lexical features are transferred to the creole is a complex process. While creoles are generally stable, the prominence of some features may be much stronger with certain demographics or in some linguistic situations. This paper makes several contributions: We collect existing corpora and release models for Haitian Creole, Nigerian Pidgin English, and Singaporean Colloquial English. We evaluate these models on intrinsic and extrinsic tasks. Motivated by the above literature, we compare standard language models with distributionally robust ones and find that, somewhat surprisingly, the standard language models are superior to the distributionally robust ones. We investigate whether this is an effect of over-parameterization or relative distributional stability, and find that the difference persists in the absence of over-parameterization, and that drift is limited, confirming the relative stability of creole languages.
AB - Creole languages such as Nigerian Pidgin English and Haitian Creole are under-resourced and largely ignored in the NLP literature. Creoles typically result from the fusion of a foreign language with multiple local languages, and what grammatical and lexical features are transferred to the creole is a complex process. While creoles are generally stable, the prominence of some features may be much stronger with certain demographics or in some linguistic situations. This paper makes several contributions: We collect existing corpora and release models for Haitian Creole, Nigerian Pidgin English, and Singaporean Colloquial English. We evaluate these models on intrinsic and extrinsic tasks. Motivated by the above literature, we compare standard language models with distributionally robust ones and find that, somewhat surprisingly, the standard language models are superior to the distributionally robust ones. We investigate whether this is an effect of over-parameterization or relative distributional stability, and find that the difference persists in the absence of over-parameterization, and that drift is limited, confirming the relative stability of creole languages.
U2 - 10.18653/v1/2021.conll-1.5
DO - 10.18653/v1/2021.conll-1.5
M3 - Article in proceedings
SP - 58
EP - 71
BT - Proceedings of the 25th Conference on Computational Natural Language Learning
PB - Association for Computational Linguistics
T2 - 25th Conference on Computational Natural Language Learning
Y2 - 1 November 2021 through 1 November 2021
ER -
ID: 299208351