Table2Vec: Neural Word and Entity Embeddings for Table Population and Retrieval
This addresses the challenge of efficiently processing and retrieving structured table knowledge for applications in data management and information retrieval, though it is incremental as it builds on existing retrieval models.
The paper tackles the problem of embedding tabular data (captions, headings, cells) into vector spaces using neural language modeling to improve table-related tasks like row/column population and table retrieval. The result shows that these embeddings significantly enhance state-of-the-art baselines in evaluations.
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.