TY  - JOUR
AU  - Khan, Aftab Ahmad
AU  - Khan, Wahab
AU  - Khan, Muhammad Alamzeb
AU  - Khan, Khairullah
AU  - Khan, Fida Muhammad
AU  - Rahman, Atta Ur
AU  - Bilal, Hazrat
AU  - Monirul, Islam Md
PY  - 2025
DA  - 2025/06/30
TI  - Comparison of Machine Learning and Deep Learning Models for Part-of-Speech Tagging
JO  - ICCK Transactions on Advanced Computing and Systems
T2  - ICCK Transactions on Advanced Computing and Systems
JF  - ICCK Transactions on Advanced Computing and Systems
VL  - 1
IS  - 2
SP  - 106
EP  - 116
DO  - 10.62762/TACS.2025.493945
UR  - https://www.icck.org/article/abs/TACS.2025.493945
KW  - machine learning
KW  - part of speech tagging
KW  - morphological structure
KW  - grammatical features
AB  - Part-of-speech (POS) tagging—the automatic assignment of grammatical categories to every token in a text corpus—is a foundational preprocessing step for AI-driven language applications such as machine translation, sentiment analysis, and information retrieval. For morphologically complex, low-resource languages such as Pashto, the scarcity of annotated data and standardised tools makes this task particularly challenging. This paper presents a systematic comparative evaluation of six machine learning (ML) and deep learning (DL) algorithms—Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), K-Nearest Neighbor (KNN), Multi-Layer Perceptron (MLP), and Naïve Bayes (NB)—on a newly constructed 32,000-token CoNLL-formatted Pashto corpus (PashtoPoSTags). Each model is assessed by token-level accuracy, the standard metric for POS tagging evaluation. Decision Tree achieved the highest accuracy of 94.34%, followed by KNN with Jaccard distance (94.14%) and KNN with Euclidean distance (93.97%). Random Forest and SVM both exceeded the 90% threshold, while MLP with Tanh activation reached 87.25% and the best Naïve Bayes variant (Complement NB) attained 83.96%. Results show that classical ML algorithms with carefully engineered n-gram features provide computationally efficient and interpretable baselines for POS tagging in resource-constrained settings, and that PashtoPoSTags offers a reproducible benchmark for future Pashto NLP research.
SN  - 3068-7969
PB  - Institute of Central Computation and Knowledge
LA  - English
ER  - 

@article{Khan2025Comparison,
  author = {Aftab Ahmad Khan and Wahab Khan and Muhammad Alamzeb Khan and Khairullah Khan and Fida Muhammad Khan and Atta Ur Rahman and Hazrat Bilal and Islam Md Monirul},
  title = {Comparison of Machine Learning and Deep Learning Models for Part-of-Speech Tagging},
  journal = {ICCK Transactions on Advanced Computing and Systems},
  year = {2025},
  volume = {1},
  number = {2},
  pages = {106-116},
  doi = {10.62762/TACS.2025.493945},
  url = {https://www.icck.org/article/abs/TACS.2025.493945},
  abstract = {Part-of-speech (POS) tagging—the automatic assignment of grammatical categories to every token in a text corpus—is a foundational preprocessing step for AI-driven language applications such as machine translation, sentiment analysis, and information retrieval. For morphologically complex, low-resource languages such as Pashto, the scarcity of annotated data and standardised tools makes this task particularly challenging. This paper presents a systematic comparative evaluation of six machine learning (ML) and deep learning (DL) algorithms—Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), K-Nearest Neighbor (KNN), Multi-Layer Perceptron (MLP), and Naïve Bayes (NB)—on a newly constructed 32,000-token CoNLL-formatted Pashto corpus (PashtoPoSTags). Each model is assessed by token-level accuracy, the standard metric for POS tagging evaluation. Decision Tree achieved the highest accuracy of 94.34\%, followed by KNN with Jaccard distance (94.14\%) and KNN with Euclidean distance (93.97\%). Random Forest and SVM both exceeded the 90\% threshold, while MLP with Tanh activation reached 87.25\% and the best Naïve Bayes variant (Complement NB) attained 83.96\%. Results show that classical ML algorithms with carefully engineered n-gram features provide computationally efficient and interpretable baselines for POS tagging in resource-constrained settings, and that PashtoPoSTags offers a reproducible benchmark for future Pashto NLP research.},
  keywords = {machine learning, part of speech tagging, morphological structure, grammatical features},
  issn = {3068-7969},
  publisher = {Institute of Central Computation and Knowledge}
}