The enrichment of tabular datasets using external sources has gained significant attention in recent years. Existing solutions, however, either ignore external unstructured data completely or devise dataset-specific solutions. In this study, we proposed Few-Shot Transformer based Enrichment (FeSTE), a generic and robust framework for the enrichment of tabular datasets using unstructured data. By training over multiple datasets, our approach is able to develop generic models that can be applied to additional datasets with minimal training (i.e., few-shot). Our approach is based on an adaptation of BERT, for which we present a novel finetuning approach that reformulates the tuples of the datasets as sentences. Our evaluation, conducted on 17 datasets, shows that FeSTE is able to generate high quality features and significantly outperform existing fine-tuning solutions.
|State||Published - 2022|
|Event||Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics - |
Duration: 22 May 2022 → 27 May 2022
|Conference||Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics|
|Period||22/05/22 → 27/05/22|