Evaluating Pixel Language Models on Non-Standardized Languages
Muñoz-Ortiz, Alberto, Blaschke, Verena, Plank, Barbara
–arXiv.org Artificial Intelligence
We explore the potential of pixel-based models for transfer learning from standard languages to dialects. These models convert text into images that are divided into patches, enabling a continuous vocabulary representation that proves especially useful for out-of-vocabulary words common in dialectal data. Using German as a case study, we compare the performance of pixel-based models to token-based models across various syntactic and semantic tasks. Our results show that pixel-based models outperform token-based models in part-of-speech tagging, dependency parsing and intent detection for zero-shot dialect evaluation by up to 26 percentage points in some scenarios, though not in Standard German. However, pixel-based models fall short in topic classification. These findings emphasize the potential of pixel-based models for handling dialectal data, though further research should be conducted to assess their effectiveness in various linguistic contexts.
arXiv.org Artificial Intelligence
Dec-12-2024
- Country:
- Asia > Singapore (0.04)
- North America
- Dominican Republic (0.04)
- United States > Minnesota
- Hennepin County > Minneapolis (0.14)
- Europe
- Spain (0.04)
- Netherlands (0.04)
- Switzerland
- Basel-City > Basel (0.04)
- Zürich > Zürich (0.04)
- Ireland > Leinster
- County Dublin > Dublin (0.04)
- Germany > Bavaria
- Upper Bavaria > Munich (0.04)
- France
- Île-de-France > Paris
- Paris (0.04)
- Provence-Alpes-Côte d'Azur > Bouches-du-Rhône
- Marseille (0.04)
- Île-de-France > Paris
- Croatia > Dubrovnik-Neretva County
- Dubrovnik (0.05)
- Bulgaria > Sofia City Province
- Sofia (0.04)
- Genre:
- Research Report > New Finding (0.69)
- Technology: