@inproceedings{tur-traum-2022-comparing,
    title = "Comparing Approaches to Language Understanding for Human-Robot Dialogue: An Error Taxonomy and Analysis",
    author = "Tur, Ada  and
      Traum, David",
    editor = "Calzolari, Nicoletta  and
      B{\'e}chet, Fr{\'e}d{\'e}ric  and
      Blache, Philippe  and
      Choukri, Khalid  and
      Cieri, Christopher  and
      Declerck, Thierry  and
      Goggi, Sara  and
      Isahara, Hitoshi  and
      Maegaard, Bente  and
      Mariani, Joseph  and
      Mazo, H{\'e}l{\`e}ne  and
      Odijk, Jan  and
      Piperidis, Stelios",
    booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
    month = jun,
    year = "2022",
    address = "Marseille, France",
    publisher = "European Language Resources Association",
    url = "https://preview.aclanthology.org/fix-sig-urls/2022.lrec-1.625/",
    pages = "5813--5820",
    abstract = "In this paper, we compare two different approaches to language understanding for a human-robot interaction domain in which a human commander gives navigation instructions to a robot. We contrast a relevance-based classifier with a GPT-2 model, using about 2000 input-output examples as training data. With this level of training data, the relevance-based model outperforms the GPT-2 based model 79{\%} to 8{\%}. We also present a taxonomy of types of errors made by each model, indicating that they have somewhat different strengths and weaknesses, so we also examine the potential for a combined model."
}