Hierarchical Multi-task learning framework for Isometric-Speech Language Translation

This paper presents our submission for the shared task on isometric neural machine translation at International Conference on Spoken Language Translation (IWSLT). There are numerous state-of-art models for translation problems. However, these models lack any length constraint to produce short or long outputs from the source text. This paper proposes a hierarchical approach to generate isometric translation on the MUST-C dataset. We achieve a BERTscore of 0.85, a length ratio of 1.087, a BLEU score of 42.3, and a length range of 51.03%. On the blind dataset provided by the task organizers, we obtained a BERTscore of 0.80, a length ratio of 1.10, and a length range of 47.5%. We have made our code public hee https://github.com/aakash0017/Machine-Translation-ISWLT.