E-TSL: A Continuous Educational Turkish Sign Language Dataset with Baseline Methods
This work addresses sign language translation for Turkish, an under-resourced domain, but is incremental as it primarily introduces a dataset and baseline methods without major methodological breakthroughs.
The study tackled the problem of translating continuous Turkish Sign Language from educational videos by introducing the E-TSL dataset and developing baseline models, with the GNN-T model achieving 19.13% BLEU-1 and 3.28% BLEU-4 scores, highlighting significant challenges due to the language's agglutinative nature and rare words.
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.