Learning Semantic Annotations for Tabular Data

Abstract

The usefulness of tabular data such as web tables critically depends on understanding their semantics. This study focuses on column type prediction for tables without any meta data. Unlike traditional lexical matching-based methods, we propose a deep prediction model that can fully exploit a table's contextual semantics, including table locality features learned by a Hybrid Neural Network (HNN), and inter-column semantics features learned by a knowledge base (KB) lookup and query answering algorithm.It exhibits good performance not only on individual table sets, but also when transferring from one table set to another.

7 pages

References in corpus (2)

• Adam: A Method for Stochastic Optimization
• Data Curation with Deep Learning [Vision]

Cited by in corpus (5)

• SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training
• TURL: Table Understanding through Representation Learning
• Semantic Labeling Using a Deep Contextualized Language Model
• Semantic Annotation for Tabular Data
• Proceedings of the First Workshop on Weakly Supervised Learning (WeaSuL)