Learning Semantic Annotations for Tabular Data

30 May 2019  ·  Jiaoyan Chen, Ernesto Jimenez-Ruiz, Ian Horrocks, Charles Sutton ·

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.

PDF Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Column Type Annotation T2Dv2 HNN + P2Vec Accuracy (%) 96.6 # 1
Column Type Annotation WikipediaGS-CTA HNN Accuracy (%) 65.5 # 2

Methods


No methods listed for this paper. Add relevant methods here