@article{gritta-etal-2021-conversation,
    title = "Conversation Graph: Data Augmentation, Training, and Evaluation for Non-Deterministic Dialogue Management",
    author = "Gritta, Milan  and
      Lampouras, Gerasimos  and
      Iacobacci, Ignacio",
    editor = "Roark, Brian  and
      Nenkova, Ani",
    journal = "Transactions of the Association for Computational Linguistics",
    volume = "9",
    year = "2021",
    address = "Cambridge, MA",
    publisher = "MIT Press",
    url = "https://preview.aclanthology.org/ingest_wac_2008/2021.tacl-1.3/",
    doi = "10.1162/tacl_a_00352",
    pages = "36--52",
    abstract = "Task-oriented dialogue systems typically rely on large amounts of high-quality training data or require complex handcrafted rules. However, existing datasets are often limited in size con- sidering the complexity of the dialogues. Additionally, conventional training signal in- ference is not suitable for non-deterministic agent behavior, namely, considering multiple actions as valid in identical dialogue states. We propose the Conversation Graph (ConvGraph), a graph-based representation of dialogues that can be exploited for data augmentation, multi- reference training and evaluation of non- deterministic agents. ConvGraph generates novel dialogue paths to augment data volume and diversity. Intrinsic and extrinsic evaluation across three datasets shows that data augmentation and/or multi-reference training with ConvGraph can improve dialogue success rates by up to 6.4{\%}."
}