← Search

Sihan Tan

2 accepted papers

2025

Improvement in Sign Language Translation Using Text CTC Alignment

COLING 2025main

Current sign language translation (SLT) approaches often rely on gloss-based supervision with Connectionist Temporal Classification (CTC), limiting their ability to handle non-monotonic alignments between sign language video and spoken text. In this work, we propose a novel method combining joint CT…

2025

Multilingual Gloss-free Sign Language Translation: Towards Building a Sign Language Foundation Model

ACL 2025short

Sign Language Translation (SLT) aims to convert sign language (SL) videos into spoken language text, thereby bridging the communication gap between the sign and the spoken community. While most existing works focus on translating a single SL into a single spoken language (one-to-one SLT), leveraging…