Generating Table Vector Representations
Aneta Koleva, Martin Ringsquandl, Mitchell Joblin, Volker Tresp

TL;DR
This paper evaluates various methods for generating vector representations of web tables to improve table classification, highlighting the potential of dedicated table encoding models over transfer learning.
Contribution
It introduces a formal definition for table classification and compares five different approaches, emphasizing the effectiveness of dedicated table encoding models.
Findings
Transfer learning methods achieve high F1 scores.
Dedicated table encoding models capture richer semantics.
Evaluation framework for table-to-class annotation methods.
Abstract
High-quality Web tables are rich sources of information that can be used to populate Knowledge Graphs (KG). The focus of this paper is an evaluation of methods for table-to-class annotation, which is a sub-task of Table Interpretation (TI). We provide a formal definition for table classification as a machine learning task. We propose an experimental setup and we evaluate 5 fundamentally different approaches to find the best method for generating vector table representations. Our findings indicate that although transfer learning methods achieve high F1 score on the table classification task, dedicated table encoding models are a promising direction as they appear to capture richer semantics.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsData Quality and Management · Topic Modeling · Biomedical Text Mining and Ontologies
