@inproceedings{bhatnagar-etal-2022-hierarchical,
    title = "Hierarchical Multi-task learning framework for Isometric-Speech Language Translation",
    author = "Bhatnagar, Aakash  and
      Bhavsar, Nidhir  and
      Singh, Muskaan  and
      Motlicek, Petr",
    booktitle = "Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022)",
    month = may,
    year = "2022",
    address = "Dublin, Ireland (in-person and online)",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.iwslt-1.35",
    doi = "10.18653/v1/2022.iwslt-1.35",
    pages = "379--385",
    abstract = "This paper presents our submission for the shared task on isometric neural machine translation in 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. In this paper, we propose a hierarchical approach to generate isometric translation on 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 obtain a BERTscore of 0.80, a length ratio of 1.10 and a length range of 47.5{\%}. We have made our code public here https://github.com/aakash0017/Machine-Translation-ISWLT",
}