Metadata-less Dataset Recommendation Leveraging Dataset Embeddings by Pre-trained Tabular Language Models

The acceleration of data-driven business and research through the use of third-party datasets has led to the emergence of data platforms that enable cross-disciplinary data exchange, thereby increasing the need for dataset recommendations. In this climate, traditional retrieval systems, such as explanatory information in metadata, have limitations in terms of the reliability of metadata descriptions and their creation cost. This study proposes a method for recommending datasets by leveraging actual dataset information without relying on meta-data. We performed two metric learning methods, unsupervised contrastive learning and table-query metric learning, utilizing pre-trained tabular language models (TaLMs). The experimental results suggest that these metric learning methods can obtain representations that are more consistent with the labels representing the topics of the datasets. Moreover, our embeddings without metadata performed as well as those with metadata, suggesting that appropriate data extraction and clustering can be performed even in cases where metadata are sparse or incomplete.