Sign Language Machine Translation

The automatic translation of written or spoken text into a signed language (or vice versa) using computational methods, typically producing output as an animated signing avatar or, less commonly, as recorded video clips. Because signed languages such as American Sign Language (ASL) have their own grammar, vocabulary, and spatial-visual modality — rather than being signed versions of the surrounding spoken language — translation is substantially harder than text-to-text MT between two spoken languages and requires modeling three-dimensional movement, facial expressions, eye gaze, and the use of signing space. Sign language MT is promoted as an accessibility tool for deaf users with low literacy in the majority written language, though the Deaf community has raised significant concerns about quality, consent, and the tendency of signing-avatar systems to be deployed in place of human interpreters rather than alongside them.