Multilingual Conceptual Coverage in Text-to-Image Models
Saxon, Michael, Wang, William Yang
–arXiv.org Artificial Intelligence
We propose "Conceptual Coverage Across Languages" (CoCo-CroLa), a technique for benchmarking the degree to which any generative text-to-image system provides multilingual parity to its training language in terms of tangible nouns. For each model we can assess "conceptual coverage" of a given target language relative to a source language by comparing the population of images generated for a series of tangible nouns in the source language to the population of images generated for each noun under translation in the target language. This technique allows us to estimate how well-suited a model is to a target language as well as identify model-specific weaknesses, spurious correlations, and biases without a-priori assumptions. We demonstrate how it can be used to benchmark T2I models in terms of multilinguality, and how despite its simplicity it is a good proxy for impressive generalization.
arXiv.org Artificial Intelligence
Jun-2-2023
- Country:
- Oceania > Australia
- North America
- United States
- New York > New York County
- New York City (0.04)
- Minnesota > Hennepin County
- Minneapolis (0.14)
- California > Santa Barbara County
- Santa Barbara (0.04)
- New York > New York County
- Puerto Rico > San Juan
- San Juan (0.04)
- Canada > Alberta
- United States
- Europe
- Sweden > Uppsala County
- Uppsala (0.04)
- Denmark > Capital Region
- Copenhagen (0.04)
- Sweden > Uppsala County
- Asia
- China > Hong Kong (0.04)
- Middle East
- Israel (0.04)
- UAE > Abu Dhabi Emirate
- Abu Dhabi (0.04)
- Genre:
- Research Report (0.50)
- Technology: