Ensemble-Based Approach for Amazigh POS Tagging: Leveraging Multiple Models for Enhanced Performance in Low-Resource Language Processing
Information · 05.08.2026 · 17 (8) · 753
DOI: 10.3390/info17080753 ↗Kurz gefasst
Fachartikel in der Zeitschrift Information, online erschienen am 05.08.2026. Verfasst von Abdelouahed Moussaoui und 3 weiteren Autor:innen. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Part-of-Speech (POS) tagging is a foundational task in Natural Language Processing (NLP), yet it remains challenging for low-resource and morphologically rich languages such as Amazigh. This paper proposes a hybrid ensemble framework for Amazigh POS tagging that integrates three complementary models: a Bidirectional Long Short-Term Memory network (BiLSTM), a Conditional Random Field model (CRF), and a rule-based morphological analyzer (RBMA). Rather than treating prior results obtained on different corpora and tag inventories as directly comparable, the study evaluates all proposed components under a common 54-tag experimental setting based on the publicly available Amazigh Linguistic Dataset. Three ensemble strategies are examined: majority voting, validation-weighted voting, and logistic-regression stacking. An additional late-fusion ablation applies hard and soft RBMA constraints to CRF and Stacking outputs; hard masking degrades performance substantially, whereas soft masking is more robust but remains below unconstrained decoding. The best micro-level performance is obtained by the stacking ensemble, which reaches 98.51% Micro-F1/accuracy, whereas the boosting-like weighted ensemble obtains the strongest Macro-F1 among the ensemble variants, reaching 74.24%. These results show that hybrid ensemble methods can improve token-level accuracy in low-resource POS tagging, while also revealing a trade-off between frequent-tag accuracy and rare-tag robustness. The findings highlight the usefulness of combining neural, probabilistic, and rule-based information for Amazigh POS tagging, and point to class-balanced meta-learning and character/subword representations as important directions for improving rare and out-of-vocabulary categories.
Zitieren
APA
Moussaoui, A., Azalmad, N., Bahassine, S., & Housni, K. (2026). Ensemble-Based Approach for Amazigh POS Tagging: Leveraging Multiple Models for Enhanced Performance in Low-Resource Language Processing. Information, 17(8), 753. https://doi.org/10.3390/info17080753
Vancouver
Moussaoui A, Azalmad N, Bahassine S, Housni K. Ensemble-Based Approach for Amazigh POS Tagging: Leveraging Multiple Models for Enhanced Performance in Low-Resource Language Processing. Information. 2026;17(8):753. doi:10.3390/info17080753
BibTeX
@article{Moussaoui2026,
author = {Moussaoui, Abdelouahed and Azalmad, Nor-Eddine and Bahassine, Said and Housni, Khalid},
title = {Ensemble-Based Approach for Amazigh POS Tagging: Leveraging Multiple Models for Enhanced Performance in Low-Resource Language Processing},
journal = {Information},
year = {2026},
volume = {17},
number = {8},
pages = {753},
doi = {10.3390/info17080753}
}
EUVIMED