ORCID: https://orcid.org/0000-0002-9944-4108
(November 2021):
Drift Detection in Text Data with Document Embeddings.
Intelligent Data Engineering and Automated Learning – IDEAL 2021, Manchester, United Kingdom, November 25-27, 2021.
In: Intelligent Data Engineering and Automated Learning – IDEAL 2021,
Vol. 13113
Cham: Springer. pp. 107-118
Abstract
Collections of text documents such as product reviews and microblogs often evolve over time. In practice, however, classifiers trained on them are updated infrequently, leading to performance degradation over time. While approaches for automatic drift detection have been proposed, they were often designed for low-dimensional sensor data, and it is unclear how well they perform for state-of-the-art text classifiers based on high-dimensional document embeddings. In this paper, we empirically compare drift detectors on document embeddings on two benchmarking datasets with varying amounts of drift. Our results show that multivariate drift detectors based on the Kernel Two-Sample Test and Least-Squares Density Difference outperform univariate drift detectors based on the Kolmogorov-Smirnov Test. Moreover, our experiments show that current drift detectors perform better on smaller embedding dimensions.
Item Type: | Conference or Workshop Item (Paper) |
---|---|
Form of publication: | Publisher's Version |
Faculties: | Mathematics, Computer Science and Statistics > Computer Science > Artificial Intelligence and Machine Learning |
Subjects: | 000 Computer science, information and general works > 000 Computer science, knowledge, and systems |
ISSN: | 0302-9743 |
Place of Publication: | Cham |
Language: | English |
Item ID: | 92511 |
Date Deposited: | 18. Jul 2022, 12:39 |
Last Modified: | 18. Jul 2022, 12:39 |