Taxonomic Loss for Morphological Glossing of Low-Resource Languages
Domain:
natural language processingRecord type:
paper
Creator:
GinPal
Host:
Morpheme glossing is a critical task in automated language documentation and can benefit other downstream applications greatly. While state-of-the-art glossing systems perform very well for languages with large amounts of existing data, it is more difficult to create useful models for low-resource languages. In this paper, we propose the use of a taxonomic loss function that exploits morphological information to make morphological glossing more performant when data is scarce. We find that while the use of this loss function does not outperform a standard loss function with regards to single-label prediction accuracy, it produces better predictions when considering the top-n predicted labels. We suggest this property makes the taxonomic loss function useful in a human-in-the-loop annotation setting.
Similar
Morphological Analysis of Sahidic Coptic for Automatic GlossingMorphological Segmentation to Improve Crosslingual Word Embeddings for Low Resource LanguagesPrompt and circumstance: A word-by-word LLM prompting approach to interlinear glossing for low-resource languagesOn the Importance of Subword Information for Morphological Tasks in Truly Low-Resource LanguagesGlossing in Semitic languagesMorphological Complexity and Cross-Lingual Alignment Degradation in English Intermediate-Task Training for Low-Resource Languages