Papers by Zed Sehyr
The American Sign Language Knowledge Graph: Infusing ASL Models with Linguistic Knowledge (2025.findings-naacl)
Copied to clipboard
| Challenge: | Sign language models could make language technologies more accessible to deaf and hard-of-hearing signers, but the supply of accurately labeled data struggles to meet the demand associated with training large, end-to-end architectures. |
| Approach: | They construct an American Sign Language Knowledge Graph from 11 sources of linguistic knowledge and use it to train neuro-symbolic models on ASL video input tasks. |
| Outcome: | The proposed model achieves 91% accuracies for isolated sign recognition, 14% for predicting the semantic features of unseen signs, and 36% for classifying the topic of Youtube-ASL videos. |
Improving Sign Recognition with Phonology (2023.eacl-main)
Copied to clipboard
| Challenge: | Existing work does not consider sign language phonology, but none leverages it . a recent study has shown that sign language recognition models lack structure . |
| Approach: | They explicitly recognize the role of phonology in sign production to train models for isolated sign language recognition . they train models that take in pose estimations of a signer producing a single sign to predict its phonological characteristics . |
| Outcome: | The proposed model improves sign recognition accuracy by 9% on the WLASL benchmark . the study could accelerate linguistic research in the domain of signed languages . |