Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2408.00283 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914895485730816 |
|---|---|
| author | Mittal, Surbhi Sudan, Arnav Vatsa, Mayank Singh, Richa Glaser, Tamar Hassner, Tal |
| author_facet | Mittal, Surbhi Sudan, Arnav Vatsa, Mayank Singh, Richa Glaser, Tamar Hassner, Tal |
| contents | This research investigates biases in text-to-image (TTI) models for the Indic languages widely spoken across India. It evaluates and compares the generative performance and cultural relevance of leading TTI models in these languages against their performance in English. Using the proposed IndicTTI benchmark, we comprehensively assess the performance of 30 Indic languages with two open-source diffusion models and two commercial generation APIs. The primary objective of this benchmark is to evaluate the support for Indic languages in these models and identify areas needing improvement. Given the linguistic diversity of 30 languages spoken by over 1.4 billion people, this benchmark aims to provide a detailed and insightful analysis of TTI models' effectiveness within the Indic linguistic landscape. The data and code for the IndicTTI benchmark can be accessed at https://iab-rubric.org/resources/other-databases/indictti. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_00283 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Navigating Text-to-Image Generative Bias across Indic Languages Mittal, Surbhi Sudan, Arnav Vatsa, Mayank Singh, Richa Glaser, Tamar Hassner, Tal Computation and Language Computer Vision and Pattern Recognition This research investigates biases in text-to-image (TTI) models for the Indic languages widely spoken across India. It evaluates and compares the generative performance and cultural relevance of leading TTI models in these languages against their performance in English. Using the proposed IndicTTI benchmark, we comprehensively assess the performance of 30 Indic languages with two open-source diffusion models and two commercial generation APIs. The primary objective of this benchmark is to evaluate the support for Indic languages in these models and identify areas needing improvement. Given the linguistic diversity of 30 languages spoken by over 1.4 billion people, this benchmark aims to provide a detailed and insightful analysis of TTI models' effectiveness within the Indic linguistic landscape. The data and code for the IndicTTI benchmark can be accessed at https://iab-rubric.org/resources/other-databases/indictti. |
| title | Navigating Text-to-Image Generative Bias across Indic Languages |
| topic | Computation and Language Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.00283 |