@inproceedings{tyen-etal-2022-towards,
    title = "Towards an open-domain chatbot for language practice",
    author = "Tyen, Gladys  and
      Brenchley, Mark  and
      Caines, Andrew  and
      Buttery, Paula",
    editor = {Kochmar, Ekaterina  and
      Burstein, Jill  and
      Horbach, Andrea  and
      Laarmann-Quante, Ronja  and
      Madnani, Nitin  and
      Tack, Ana{\"i}s  and
      Yaneva, Victoria  and
      Yuan, Zheng  and
      Zesch, Torsten},
    booktitle = "Proceedings of the 17th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2022)",
    month = jul,
    year = "2022",
    address = "Seattle, Washington",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2022.bea-1.28/",
    doi = "10.18653/v1/2022.bea-1.28",
    pages = "234--249",
    abstract = "State-of-the-art chatbots for English are now able to hold conversations on virtually any topic (e.g. Adiwardana et al., 2020; Roller et al., 2021). However, existing dialogue systems in the language learning domain still use hand-crafted rules and pattern matching, and are much more limited in scope. In this paper, we make an initial foray into adapting open-domain dialogue generation for second language learning. We propose and implement decoding strategies that can adjust the difficulty level of the chatbot according to the learner{'}s needs, without requiring further training of the chatbot. These strategies are then evaluated using judgements from human examiners trained in language education. Our results show that re-ranking candidate outputs is a particularly effective strategy, and performance can be further improved by adding sub-token penalties and filtering."
}