Papers by Shaomei Wu
Lost in Translation: Benchmarking Commercial Machine Translation Models for Dyslexic-Style Text (2025.findings-acl)
Copied to clipboard
| Challenge: | Dyslexia affects writing, leading to unique patterns such as letter and homophone swapping. |
| Approach: | They examine the fairness of four commercial machine translation systems towards dyslexic text through a systematic audit using both synthetically generated and real writing from individuals with dyslexia. |
| Outcome: | The proposed system audits show that it is fair to use synthetic and synthetic dyslexic text and real writing from people with dyslexia. |