Benchmarking POS Tagging for the Tajik Language: A Comparative Study of Neural Architectures on the TajPersParallel Corpus

TL;DR

This study benchmarks neural architectures for Tajik POS tagging using the TajPersParallel corpus, revealing the strengths of multilingual models like mBERT with LoRA in context-independent classification tasks.

Contribution

It provides the first systematic comparison of neural models for Tajik POS tagging, highlighting the effectiveness of multilingual transformers and the impact of context on morphological analysis.

Findings

mBERT + LoRA achieved the highest macro F1-score of 0.11 and weighted F1-score of 0.62.

Models struggled with rare function words due to lack of syntactic context.

Zero-shot evaluation showed Tajik's closest typological relations to Persian and Russian.

Abstract

This paper presents the first benchmark for the task of automatic part-of-speech (POS) tagging for the Tajik language. Despite the existence of multilingual language models demonstrating high effectiveness for many of the world's languages, their capacity for grammatical analysis of Tajik has remained unexplored until now. The aim of this study is to fill this gap through a systematic comparison of classical neural network architectures and modern multilingual transformers. Experiments were conducted on the TajPersParallel corpus, a parallel lexical resource comprising approximately 44,000 dictionary entries. Due to the absence of full-fledged example sentences in the current version of the corpus, the task was performed at the level of isolated lexical units, representing a challenging case of context-independent classification. The study compares the following architectures: a recurrent BiLSTM-CRF model, as well as multilingual models XLM-RoBERTa (large), mBERT, ParsBERT (Persian), and ruBERT (Russian), adapted using the parameter-efficient fine-tuning method LoRA. The testing results showed that the best performance is achieved by the mBERT + LoRA model (macro F1-score = 0.11, weighted F1-score = 0.62). It was established that in the absence of syntactic context, all models experience significant difficulty in resolving morphological ambiguity, successfully classifying primarily high-frequency classes ("noun," "adjective") while demonstrating zero effectiveness for rare function words. Zero-shot evaluation revealed the greatest typological proximity of Tajik to Persian (ParsBERT) and Russian (ruBERT). The obtained results form a foundation for further research and development in the field of automatic processing of the Tajik language.