A Benchmark for Evaluating Machine Translation Metrics on Dialects Without Standard Orthography
Aepli, Noëmi, Amrhein, Chantal, Schottmann, Florian, Sennrich, Rico
–arXiv.org Artificial Intelligence
For sensible progress in natural language processing, it is important that we are aware of the limitations of the evaluation metrics we use. In this work, we evaluate how robust metrics are to non-standardized dialects, i.e. spelling differences in language varieties that do not have a standard orthography. To investigate this, we collect a dataset of human translations and human judgments for automatic machine translations from English to two Swiss German dialects. We further create a challenge set for dialect variation and benchmark existing metrics' performances. Our results show that existing metrics cannot reliably evaluate Swiss German text generation outputs, especially on segment level. We propose initial design adaptations that increase robustness in the face of non-standardized dialects, although there remains much room for further improvement. The dataset, code, and models are available here: https://github.com/textshuttle/dialect_eval
arXiv.org Artificial Intelligence
Nov-28-2023
- Country:
- Africa (0.04)
- Oceania
- Cook Islands (0.04)
- New Zealand > South Island
- North America
- Dominican Republic (0.04)
- United States
- Pennsylvania (0.04)
- Michigan (0.04)
- New Mexico > Santa Fe County
- Santa Fe (0.04)
- Canada
- Europe
- Germany > Berlin (0.04)
- Latvia (0.04)
- Switzerland > Zürich
- Zürich (0.04)
- Italy > Tuscany
- Florence (0.04)
- France > Provence-Alpes-Côte d'Azur
- Bouches-du-Rhône > Marseille (0.04)
- Spain
- Valencian Community > Valencia Province
- Valencia (0.04)
- Catalonia > Barcelona Province
- Barcelona (0.04)
- Valencian Community > Valencia Province
- Denmark > Capital Region
- Copenhagen (0.04)
- Bulgaria > Sofia City Province
- Sofia (0.04)
- Portugal > Lisbon
- Lisbon (0.04)
- Croatia > Dubrovnik-Neretva County
- Dubrovnik (0.04)
- Ireland > Leinster
- County Dublin > Dublin (0.04)
- Belgium > Brussels-Capital Region
- Brussels (0.04)
- United Kingdom > Scotland
- City of Edinburgh > Edinburgh (0.04)
- Asia
- Myanmar (0.04)
- Indonesia (0.04)
- Middle East
- Japan > Kyūshū & Okinawa
- Kyūshū > Miyazaki Prefecture > Miyazaki (0.04)
- China > Shanghai
- Shanghai (0.04)
- Genre:
- Research Report > New Finding (1.00)
- Technology: