iSign: A Benchmark for Indian Sign Language Processing

TL;DR

iSign introduces a comprehensive benchmark for Indian Sign Language processing, including a large dataset, multiple NLP tasks, and baseline models, to advance research in this under-resourced area.

Contribution

The paper releases the largest ISL-English dataset, proposes multiple NLP tasks, and provides baseline models and linguistic insights for Indian Sign Language processing.

Findings

Largest ISL dataset with 118K video-sentence pairs

Benchmarking of multiple NLP tasks for ISL

Baseline models and linguistic analysis provided

Abstract

Indian Sign Language has limited resources for developing machine learning and data-driven approaches for automated language processing. Though text/audio-based language processing techniques have shown colossal research interest and tremendous improvements in the last few years, Sign Languages still need to catch up due to the need for more resources. To bridge this gap, in this work, we propose iSign: a benchmark for Indian Sign Language (ISL) Processing. We make three primary contributions to this work. First, we release one of the largest ISL-English datasets with more than 118K video-sentence/phrase pairs. To the best of our knowledge, it is the largest sign language dataset available for ISL. Second, we propose multiple NLP-specific tasks (including SignVideo2Text, SignPose2Text, Text2Pose, Word Prediction, and Sign Semantics) and benchmark them with the baseline models for easier access to the research community. Third, we provide detailed insights into the proposed benchmarks with a few linguistic insights into the workings of ISL. We streamline the evaluation of Sign Language processing, addressing the gaps in the NLP research community for Sign Languages. We release the dataset, tasks, and models via the following website: https://exploration-lab.github.io/iSign/