MasakhaPOS: Part-of-Speech Tagging for Typologically Diverse African Languages

TL;DR

This paper introduces MasakhaPOS, a comprehensive POS dataset for 20 African languages, and explores cross-lingual transfer methods to improve POS tagging performance across typologically diverse languages.

Contribution

It provides the largest POS dataset for African languages and evaluates cross-lingual transfer techniques, highlighting the importance of language similarity and fine-tuning methods.

Findings

Transfer from similar languages improves POS tagging accuracy.

Multilingual models outperform single-language models.

Cross-lingual fine-tuning enhances performance significantly.

Abstract

In this paper, we present MasakhaPOS, the largest part-of-speech (POS) dataset for 20 typologically diverse African languages. We discuss the challenges in annotating POS for these languages using the UD (universal dependencies) guidelines. We conducted extensive POS baseline experiments using conditional random field and several multilingual pre-trained language models. We applied various cross-lingual transfer models trained with data available in UD. Evaluating on the MasakhaPOS dataset, we show that choosing the best transfer language(s) in both single-source and multi-source setups greatly improves the POS tagging performance of the target languages, in particular when combined with cross-lingual parameter-efficient fine-tuning methods. Crucially, transferring knowledge from a language that matches the language family and morphosyntactic properties seems more effective for POS tagging in unseen languages.