@inproceedings{mahajan-shaikh-2021-need,
    title = "On the Need for Thoughtful Data Collection for Multi-Party Dialogue: A Survey of Available Corpora and Collection Methods",
    author = "Mahajan, Khyati  and
      Shaikh, Samira",
    editor = "Li, Haizhou  and
      Levow, Gina-Anne  and
      Yu, Zhou  and
      Gupta, Chitralekha  and
      Sisman, Berrak  and
      Cai, Siqi  and
      Vandyke, David  and
      Dethlefs, Nina  and
      Wu, Yan  and
      Li, Junyi Jessy",
    booktitle = "Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue",
    month = jul,
    year = "2021",
    address = "Singapore and Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2021.sigdial-1.36/",
    doi = "10.18653/v1/2021.sigdial-1.36",
    pages = "338--352",
    abstract = "We present a comprehensive survey of available corpora for multi-party dialogue. We survey over 300 publications related to multi-party dialogue and catalogue all available corpora in a novel taxonomy. We analyze methods of data collection for multi-party dialogue corpora and identify several lacunae in existing data collection approaches used to collect such dialogue. We present this survey, the first survey to focus exclusively on multi-party dialogue corpora, to motivate research in this area. Through our discussion of existing data collection methods, we identify desiderata and guiding principles for multi-party data collection to contribute further towards advancing this area of dialogue research."
}