Benchmarking Commercial Intent Detection Services with Practice-Driven Evaluations



  • Haode Qi
  • Lin Pan
  • Atin Sood
  • Abhishek Shah
  • Ladislav Kunc
  • Mo Yu
  • Saloni Potdar

Published on


Intent detection is a key component of modern goal-oriented dialog systems that accomplish a user task by predicting the intent of users’ text input. There are three primary challenges in designing robust and accurate intent detection models. First, typical intent detection models require a large amount of labeled data to achieve high accuracy. Unfortunately, in practical scenarios it is more common to find small, unbalanced, and noisy datasets. Secondly, even with large training data, the intent detection models can see a different distribution of test data when being deployed in the real world, leading to poor accuracy. Finally, a practical intent detection model must be computationally efficient in both training and single query inference so that it can be used continuously and re-trained frequently. We benchmark intent detection methods on a variety of datasets. Our results show that Watson Assistant’s intent detection model outperforms other commercial solutions and is comparable to large pretrained language models while requiring only a fraction of computational resources and training data. Watson Assistant demonstrates a higher degree of robustness when the training and test distributions differ.

This paper has been published at NAACL Industrial Track 2021

Please cite our work using the BibTeX below.

    title = "Benchmarking Commercial Intent Detection Services with Practice-Driven Evaluations",
    author = "Qi, Haode  and
      Pan, Lin  and
      Sood, Atin  and
      Shah, Abhishek  and
      Kunc, Ladislav  and
      Yu, Mo  and
      Potdar, Saloni",
    booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Papers",
    month = jun,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "",
    pages = "304--310",
Close Modal