Document Type
Article
Publication Date
10-2024
Publisher
Elsevier
Abstract
Missing data in tabular dataset is a common issue as the performance of downstream tasks usually depends on the completeness of the training dataset. Previous missing data imputation methods focus on numeric and categorical columns, but we propose a novel end-to-end approach called Table Transformers for Imputing Textual Attributes (TTITA) based on the transformer to impute unstructured textual columns using other columns in the table. We conduct extensive experiments on three datasets, and our approach shows competitive performance outperforming baseline models such as recurrent neural networks and Llama2. The performance improvement is more significant when the target sequence has a longer length. Additionally, we incorporate multi-task learning to simultaneously impute for heterogeneous columns, boosting the performance for text imputation. We also qualitatively compare with ChatGPT for realistic applications.
Recommended Citation
Wei, T.-R., Wang, Y., Inoue, Y., Wu, H.-T., & Fang, Y. (2024). Table Transformers for imputing textual attributes. Pattern Recognition Letters, 186, 258–264. https://doi.org/10.1016/j.patrec.2024.09.023
Comments
© 2024 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).