Generating Signed Language Instructions in Large-Scale Dialogue Systems

TL;DR

This paper presents a novel goal-oriented conversational AI system that generates American Sign Language instructions, integrating multimodal retrieval, large language models, and community insights to enhance accessibility and effectiveness.

Contribution

It introduces the first implementation of a sign language instruction system within a large-scale dialogue platform, combining retrieval methods, LLMs, and community engagement.

Findings

User feedback shows comparable ratings for signing and non-signing variants.

High retrieval accuracy and text-generation quality demonstrated by BERTScore.

Open-source code and datasets facilitate further research and development.

Abstract

We introduce a goal-oriented conversational AI system enhanced with American Sign Language (ASL) instructions, presenting the first implementation of such a system on a worldwide multimodal conversational AI platform. Accessible through a touch-based interface, our system receives input from users and seamlessly generates ASL instructions by leveraging retrieval methods and cognitively based gloss translations. Central to our design is a sign translation module powered by Large Language Models, alongside a token-based video retrieval system for delivering instructional content from recipes and wikiHow guides. Our development process is deeply rooted in a commitment to community engagement, incorporating insights from the Deaf and Hard-of-Hearing community, as well as experts in cognitive and ASL learning sciences. The effectiveness of our signing instructions is validated by user feedback, achieving ratings on par with those of the system in its non-signing variant. Additionally, our system demonstrates exceptional performance in retrieval accuracy and text-generation quality, measured by metrics such as BERTScore. We have made our codebase and datasets publicly accessible at https://github.com/Merterm/signed-dialogue, and a demo of our signed instruction video retrieval system is available at https://huggingface.co/spaces/merterm/signed-instructions.