Recipe for Zero-shot POS Tagging: Is It Useful in Realistic Scenarios?
This work addresses the challenge of POS tagging for languages with limited data, offering incremental improvements in zero-shot methods for NLP applications.
The paper tackles the problem of part-of-speech (POS) tagging for low-resource languages by investigating zero-shot approaches, finding that selecting datasets with strong linguistic relationships and high quality leads to viable results, with zero-shot models performing comparably to models trained directly on target languages in some cases.
POS tagging plays a fundamental role in numerous applications. While POS taggers are highly accurate in well-resourced settings, they lag behind in cases of limited or missing training data. This paper focuses on POS tagging for languages with limited data. We seek to identify the characteristics of datasets that make them favourable for training POS tagging models without using any labelled training data from the target language. This is a zero-shot approach. We compare the accuracies of a multilingual large language model (mBERT) fine-tuned on one or more languages related to the target language. Additionally, we compare these results with models trained directly on the target language itself. We do this for three target low-resource languages. Our research highlights the importance of accurate dataset selection for effective zero-shot POS tagging. Particularly, a strong linguistic relationship and high-quality datasets ensure optimal results. For extremely low-resource languages, zero-shot models prove to be a viable option.