Cross-lingual, Character-Level Neural Morphological Tagging
This addresses the challenge of morphological tagging for low-resource languages, though it is incremental as it builds on existing transfer learning methods.
The paper tackles the problem of insufficient supervision for morphological tagging in low-resource languages by using a cross-lingual, character-level neural transfer learning scheme, resulting in accuracy improvements of up to 30% over monolingual models.
Even for common NLP tasks, sufficient supervision is not available in many languages -- morphological tagging is no exception. In the work presented here, we explore a transfer learning scheme, whereby we train character-level recurrent neural taggers to predict morphological taggings for high-resource languages and low-resource languages together. Learning joint character representations among multiple related languages successfully enables knowledge transfer from the high-resource languages to the low-resource ones, improving accuracy by up to 30% over a monolingual model.