@inproceedings{arora-etal-2020-hint3,
    title = "{HINT}3: Raising the bar for Intent Detection in the Wild",
    author = "Arora, Gaurav  and
      Jain, Chirag  and
      Chaturvedi, Manas  and
      Modi, Krupal",
    editor = "Rogers, Anna  and
      Sedoc, Jo{\~a}o  and
      Rumshisky, Anna",
    booktitle = "Proceedings of the First Workshop on Insights from Negative Results in NLP",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2020.insights-1.16/",
    doi = "10.18653/v1/2020.insights-1.16",
    pages = "100--105",
    abstract = "Intent Detection systems in the real world are exposed to complexities of imbalanced datasets containing varying perception of intent, unintended correlations and domain-specific aberrations. To facilitate benchmarking which can reflect near real-world scenarios, we introduce 3 new datasets created from live chatbots in diverse domains. Unlike most existing datasets that are crowdsourced, our datasets contain real user queries received by the chatbots and facilitates penalising unwanted correlations grasped during the training process. We evaluate 4 NLU platforms and a BERT based classifier and find that performance saturates at inadequate levels on test sets because all systems latch on to unintended patterns in training data."
}