@inproceedings{wilken-matusov-2022-appteks,
    title = "{A}pp{T}ek{'}s Submission to the {IWSLT} 2022 Isometric Spoken Language Translation Task",
    author = "Wilken, Patrick  and
      Matusov, Evgeny",
    editor = "Salesky, Elizabeth  and
      Federico, Marcello  and
      Costa-juss{\`a}, Marta",
    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://preview.aclanthology.org/fix-sig-urls/2022.iwslt-1.34/",
    doi = "10.18653/v1/2022.iwslt-1.34",
    pages = "369--378",
    abstract = "To participate in the Isometric Spoken Language Translation Task of the IWSLT 2022 evaluation, constrained condition, AppTek developed neural Transformer-based systems for English-to-German with various mechanisms of length control, ranging from source-side and target-side pseudo-tokens to encoding of remaining length in characters that replaces positional encoding. We further increased translation length compliance by sentence-level selection of length-compliant hypotheses from different system variants, as well as rescoring of N-best candidates from a single system. Length-compliant back-translated and forward-translated synthetic data, as well as other parallel data variants derived from the original MuST-C training corpus were important for a good quality/desired length trade-off. Our experimental results show that length compliance levels above 90{\%} can be reached while minimizing losses in MT quality as measured in BERT and BLEU scores."
}