Table2vec: Neural Word And Entity Embeddings For Table Population And Retrieval

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.

Stats

• citations63
• S2 citations—
• github stars0
• HF likes0
• heat score13.55
• arxiv keydeng2019table2vec

Related papers

• Multi-modal Retrieval Of Tables And Texts Using Tri-encoder Models (2021)6.34
• Analytics Modelling Over Multiple Datasets Using Vector Embeddings (2025)2.26
• Text Embeddings For Retrieval From A Large Knowledge Base (2018)4.52
• Explore Entity Embedding Effectiveness In Entity Retrieval (2019)4.52
• Tabular Embedding Model (TEM): Finetuning Embedding Models For Tabular RAG Applications (2024)5.84
• Doctag2vec: An Embedding Based Multi-label Learning Approach For Document Tagging (2017)8.60
• Multitask Text-to-visual Embedding With Titles And Clickthrough Data (2019)0.00
• Retrieving Multi-entity Associations: An Evaluation Of Combination Modes For Word Embeddings (2019)0.00