DeepAI AI Chat
Log In Sign Up

Entity Linking in Tabular Data Needs the Right Attention

by   Miltiadis Marios Katsakioris, et al.
Heriot-Watt University

Understanding the semantic meaning of tabular data requires Entity Linking (EL), in order to associate each cell value to a real-world entity in a Knowledge Base (KB). In this work, we focus on end-to-end solutions for EL on tabular data that do not rely on fact lookup in the target KB. Tabular data contains heterogeneous and sparse context, including column headers, cell values and table captions. We experiment with various models to generate a vector representation for each cell value to be linked. Our results show that it is critical to apply an attention mechanism as well as an attention mask, so that the model can only attend to the most relevant context and avoid information dilution. The most relevant context includes: same-row cells, same-column cells, headers and caption. Computational complexity, however, grows quadratically with the size of tabular data for such a complex model. We achieve constant memory usage by introducing a Tabular Entity Linking Lite model (TELL ) that generates vector representation for a cell based only on its value, the table headers and the table caption. TELL achieves 80.8 Wikipedia tables, which is only 0.1 quadratic memory usage.


S2abEL: A Dataset for Entity Linking from Scientific Tables

Entity linking (EL) is the task of linking a textual mention to its corr...

ColNet: Embedding the Semantics of Web Tables for Column Type Prediction

Automatically annotating column types with knowledge base (KB) concepts ...

Table2Vec: Neural Word and Entity Embeddings for Table Population and Retrieval

Tables contain valuable knowledge in a structured form. We employ neural...

Tabling Optimization for Contextual Abduction

Tabling for contextual abduction in logic programming has been introduce...

On-the-fly Table Generation

Many information needs revolve around entities, which would be better an...

Automatic Table completion using Knowledge Base

Table is a popular data format to organize and present relational inform...

Benchmarking Diverse-Modal Entity Linking with Generative Models

Entities can be expressed in diverse formats, such as texts, images, or ...