EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Symmetric Affix–Context Co-Attention: A Dual-Gating Framework for Robust POS Tagging in Low-Resource MRLs

Yuan Qi, Samat Ali, Alim Murat

Symmetry · 18.09.2025 · 17 (9) · 1561

DOI: 10.3390/sym17091561 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Symmetry, online erschienen am 18.09.2025. Verfasst von Yuan Qi und 2 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Xinjiang Uyghur Autonomous Region, ational Natural Science Foundation of China Youth Program, Ministry of Education of Humanities and Social Science Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Part-of-speech (POS) tagging in low-resource, morphologically rich languages (LRLs/MRLs) remains challenging due to extensive affixation, high out-of-vocabulary (OOV) rates, and pervasive polysemy. We propose MRL-POS, a unified Transformer-CRF framework that dynamically selects informative affix features and integrates them with deep contextual embeddings via a novel dual-gating co-attention mechanism. First, a Dynamic Affix Selector adaptively adjusts n-gram ranges and frequency thresholds based on word length to ensure high-precision affix segmentation. Second, the Affix–Context Co-Attention Module employs two gating functions that conditionally amplify contextual dimensions with affix cues and vice versa, enabling robust disambiguation of complex and ambiguous forms. Third, Layer-Wise Attention Pooling aggregates multi-layer XLM-RoBERTa representations, emphasizing those most relevant for morphological and syntactic tagging. Evaluations on Uyghur, Kyrgyz, and Uzbek show that MRL-POS achieves an average F1 of 84.10%, OOV accuracy of 84.24%, and Poly-F1 of 72.14%, outperforming strong baselines by up to 8 F1 points. By explicitly modeling the symmetry between morphological affix cues and sentence-level context through a dual-gating co-attention mechanism, MRL-POS achieves a balanced fusion that both preserves local structure and captures global dependencies. Interpretability analyses confirm that 89.1% of the selected affixes align with linguistic expectations. This symmetric design not only enhances robustness in low-resource and agglutinative settings but also offers a general paradigm for symmetry-aware sequence labeling tasks.

Förderung

  • Natural Science Foundation of Xinjiang Uyghur Autonomous Region
  • ational Natural Science Foundation of China Youth Program
  • Ministry of Education of Humanities and Social Science Project

Zitieren

APA

Qi, Y., Ali, S., & Murat, A. (2025). Symmetric Affix–Context Co-Attention: A Dual-Gating Framework for Robust POS Tagging in Low-Resource MRLs. Symmetry, 17(9), 1561. https://doi.org/10.3390/sym17091561

Vancouver

Qi Y, Ali S, Murat A. Symmetric Affix–Context Co-Attention: A Dual-Gating Framework for Robust POS Tagging in Low-Resource MRLs. Symmetry. 2025;17(9):1561. doi:10.3390/sym17091561

BibTeX
@article{Qi2025,
  author = {Qi, Yuan and Ali, Samat and Murat, Alim},
  title = {Symmetric Affix–Context Co-Attention: A Dual-Gating Framework for Robust POS Tagging in Low-Resource MRLs},
  journal = {Symmetry},
  year = {2025},
  volume = {17},
  number = {9},
  pages = {1561},
  doi = {10.3390/sym17091561}
}
Kostenlos starten →