E-TSL: A Continuous Educational Turkish Sign Language Dataset with Baseline Methods

TL;DR

This paper introduces the E-TSL dataset for Turkish Sign Language, along with baseline models that address language-specific challenges, achieving promising results and benchmarking against existing datasets.

Contribution

The study presents a new continuous Turkish Sign Language dataset and develops two baseline models, including a GNN-based transformer, for sign language translation.

Findings

GNN-T achieved 19.13% BLEU-1 score

P2T-T achieved a ROUGE-L score of 22.09%

Benchmarking on PHOENIX-Weather 2014T validates the models' effectiveness

Abstract

This study introduces the continuous Educational Turkish Sign Language (E-TSL) dataset, collected from online Turkish language lessons for 5th, 6th, and 8th grades. The dataset comprises 1,410 videos totaling nearly 24 hours and includes performances from 11 signers. Turkish, an agglutinative language, poses unique challenges for sign language translation, particularly with a vocabulary where 64% are singleton words and 85% are rare words, appearing less than five times. We developed two baseline models to address these challenges: the Pose to Text Transformer (P2T-T) and the Graph Neural Network based Transformer (GNN-T) models. The GNN-T model achieved 19.13% BLEU-1 score and 3.28% BLEU-4 score, presenting a significant challenge compared to existing benchmarks. The P2T-T model, while demonstrating slightly lower performance in BLEU scores, achieved a higher ROUGE-L score of 22.09%. Additionally, we benchmarked our model using the well-known PHOENIX-Weather 2014T dataset to validate our approach.