Reliable and Interpretable Drift Detection in Streams of Short Texts
Ella Rabinovich, Matan Vetzler, Samuel Ackerman, Ateret Anaby Tavor
Abstract
Data drift is the change in model input data that is one of the key factors leading to machine learning models performance degradation over time. Monitoring drift helps detecting these issues and preventing their harmful consequences. Meaningful drift interpretation is a fundamental step towards effective re-training of the model. In this study we propose an end-to-end framework for reliable model-agnostic change-point detection and interpretation in large task-oriented dialog systems, proven effective in multiple customer deployments. We evaluate our approach and demonstrate its benefits with a novel variant of intent classification training dataset, simulating customer requests to a dialog system. We make the data publicly available.
BibTeX
@inproceedings{rabinovich-etal-2023-reliable,
title = "Reliable and Interpretable Drift Detection in Streams of Short Texts",
author = "Rabinovich, Ella and
Vetzler, Matan and
Ackerman, Samuel and
Anaby Tavor, Ateret",
editor = "Sitaram, Sunayana and
Beigman Klebanov, Beata and
Williams, Jason D",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-industry.42/",
doi = "10.18653/v1/2023.acl-industry.42",
pages = "438--446"
}