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

## TL;DR

This paper introduces Table2Vec, a neural embedding approach for tables that improves table population and retrieval tasks by capturing semantic information from table elements.

## Contribution

It proposes a novel neural embedding method for table elements and demonstrates its effectiveness in enhancing table-related retrieval and population tasks.

## Key findings

- Table embeddings significantly outperform baselines.
- Embeddings improve accuracy in row and column population.
- Enhanced retrieval performance with semantic signals.

## Abstract

Tables contain valuable knowledge in a structured form. We employ neural language modeling approaches to embed tabular data into vector spaces. Specifically, we consider different table elements, such caption, column headings, and cells, for training word and entity embeddings. These embeddings are then utilized in three particular table-related tasks, row population, column population, and table retrieval, by incorporating them into existing retrieval models as additional semantic similarity signals. Evaluation results show that table embeddings can significantly improve upon the performance of state-of-the-art baselines.