Part-of-Speech Tagging on an Endangered Language: a Parallel Griko-Italian Resource
This addresses the problem of linguistic preservation for endangered languages like Griko, though it is incremental as it applies existing methods to a new dataset.
The paper tackles part-of-speech tagging for the endangered language Griko by creating a parallel Griko-Italian resource and evaluating methods, finding that a semi-supervised approach with cross-lingual transfer achieves 72.9% accuracy and active learning improves it by over 21 percentage points.
Most work on part-of-speech (POS) tagging is focused on high resource languages, or examines low-resource and active learning settings through simulated studies. We evaluate POS tagging techniques on an actual endangered language, Griko. We present a resource that contains 114 narratives in Griko, along with sentence-level translations in Italian, and provides gold annotations for the test set. Based on a previously collected small corpus, we investigate several traditional methods, as well as methods that take advantage of monolingual data or project cross-lingual POS tags. We show that the combination of a semi-supervised method with cross-lingual transfer is more appropriate for this extremely challenging setting, with the best tagger achieving an accuracy of 72.9%. With an applied active learning scheme, which we use to collect sentence-level annotations over the test set, we achieve improvements of more than 21 percentage points.