@inproceedings{jansen-boyd-graber-2022-picard,
    title = "{P}icard understanding Darmok: A Dataset and Model for Metaphor-Rich Translation in a Constructed Language",
    author = "Jansen, Peter A.  and
      Boyd-Graber, Jordan",
    editor = "Ghosh, Debanjan  and
      Beigman Klebanov, Beata  and
      Muresan, Smaranda  and
      Feldman, Anna  and
      Poria, Soujanya  and
      Chakrabarty, Tuhin",
    booktitle = "Proceedings of the 3rd Workshop on Figurative Language Processing (FLP)",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates (Hybrid)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2022.flp-1.5/",
    doi = "10.18653/v1/2022.flp-1.5",
    pages = "34--38",
    abstract = "Tamarian, a fictional language introduced in the Star Trek episode Darmok, communicates meaning through utterances of metaphorical references, such as {\textquotedblleft}Darmok and Jalad at Tanagra{\textquotedblright} instead of {\textquotedblleft}We should work together.{\textquotedblright} This work assembles a Tamarian-English dictionary of utterances from the original episode and several follow-on novels, and uses this to construct a parallel corpus of 456 English-Tamarian utterances. A machine translation system based on a large language model (T5) is trained using this parallel corpus, and is shown to produce an accuracy of 76{\%} when translating from English to Tamarian on known utterances."
}