When Distributions Shifts: Causal Generalization for Low-Resource Languages

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Aminu, Mahi Aliyu, Chibuike, Chisom, Adebanjo, Fatimo, Awosanya, Omokolade, Oyeneye, Samuel
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911457897086976
author Aminu, Mahi Aliyu
Chibuike, Chisom
Adebanjo, Fatimo
Awosanya, Omokolade
Oyeneye, Samuel
author_facet Aminu, Mahi Aliyu
Chibuike, Chisom
Adebanjo, Fatimo
Awosanya, Omokolade
Oyeneye, Samuel
contents Machine learning models often fail under distribution shifts, a problem exacerbated in low-resource settings where limited data restricts robust generalization. Domain generalization(DG) methods address this challenge by learning representations that remain invariant across domains, frequently leveraging causal principles. In this work, we study two causal DG approaches for low-resource natural language processing. First, we apply causal data augmentation using GPT-4o-mini to generate counterfactual paraphrases for sentiment classification on the NaijaSenti Twitter corpus in Yoruba and Igbo. Second, we investigate invariant causal representation learning with the Debiasing in Aspect Review (DINER) framework for aspect-based sentiment analysis. We extend DINER to a multilingual setting by introducing Afri-SemEval, a dataset of 17 languages translated from SemEval-2014 Task. Experiments show improved robustness to unseen domains, with consistent gains from counterfactual augmentation and enhanced out-of-distribution performance from causal representation learning across multiple languages.
format Preprint
id arxiv_https___arxiv_org_abs_2510_27512
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle When Distributions Shifts: Causal Generalization for Low-Resource Languages
Aminu, Mahi Aliyu
Chibuike, Chisom
Adebanjo, Fatimo
Awosanya, Omokolade
Oyeneye, Samuel
Computation and Language
Machine learning models often fail under distribution shifts, a problem exacerbated in low-resource settings where limited data restricts robust generalization. Domain generalization(DG) methods address this challenge by learning representations that remain invariant across domains, frequently leveraging causal principles. In this work, we study two causal DG approaches for low-resource natural language processing. First, we apply causal data augmentation using GPT-4o-mini to generate counterfactual paraphrases for sentiment classification on the NaijaSenti Twitter corpus in Yoruba and Igbo. Second, we investigate invariant causal representation learning with the Debiasing in Aspect Review (DINER) framework for aspect-based sentiment analysis. We extend DINER to a multilingual setting by introducing Afri-SemEval, a dataset of 17 languages translated from SemEval-2014 Task. Experiments show improved robustness to unseen domains, with consistent gains from counterfactual augmentation and enhanced out-of-distribution performance from causal representation learning across multiple languages.
title When Distributions Shifts: Causal Generalization for Low-Resource Languages
topic Computation and Language
url https://arxiv.org/abs/2510.27512