# TabEmb: Joint Semantic-Structure Embedding for Table Annotation

arXiv: https://arxiv.org/abs/2604.18939 · HTML: https://mlsanity.com/paper/2604.18939/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 32 references that are in the map.
- First posted on arXiv 21 Apr 2026.

## Builds on (most cited first, 12 of 12)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Gated Graph Sequence Neural Networks](https://mlsanity.com/paper/1511.05493/) (2015)
- [TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data](https://mlsanity.com/paper/2005.08314/) (2020)
- [TableLlama: Towards Open Large Generalist Models for Tables](https://mlsanity.com/paper/2311.09206/) (2023)
- [TABBIE: Pretrained Representations of Tabular Data](https://mlsanity.com/paper/2105.02584/) (2021)
- [Sherlock: A Deep Learning Approach to Semantic Data Type Detection](https://mlsanity.com/paper/1905.10688/) (2019)
- [TCN: Table Convolutional Network for Web Table Interpretation](https://mlsanity.com/paper/2102.09460/) (2021)
- [Learning Semantic Annotations for Tabular Data](https://mlsanity.com/paper/1906.00781/) (2019)
- [Data Lakes: A Survey of Functions and Systems](https://mlsanity.com/paper/2106.09592/) (2021)
- [Graph Neural Network Approach to Semantic Type Detection in Tables](https://mlsanity.com/paper/2405.00123/) (2024)
- [Retrieve-and-Verify: A Table Context Selection Framework for Accurate Column Annotations](https://mlsanity.com/paper/2508.17203/) (2025)

## Built on by (most cited first, 1 of 1)

- [Interpretable Column Annotation with LLM-Symbolized Decision Process Materialization](https://mlsanity.com/paper/2607.25228/) (2026)

## Abstract (arXiv)

Table annotation is crucial for making web and enterprise tables usable in downstream NLP applications. Unlike textual data where learning semantically rich token or sentence embeddings often suffice, tables are structured combinations of columns wherein useful representations must jointly capture column's semantics and the inter-column relationships. Existing models learn by linearizing the 2D table into a 1D token sequence and encoding it with pretrained language models (PLMs) such as BERT. However, this leads to limited semantic quality and weaker generalization to unseen or rare values compared to modern LLMs, and degraded structural modeling due to 2D-to-1D flattening and context-length constraints. We propose TabEmb, which directly targets these limitations by decoupling semantic encoding from structural modeling. An LLM first produces semantically rich embeddings for each column, and a graph-based module over columns then injects relationships into the embeddings, yielding joint semantic-tructural representations for table annotation. Experiments show that TabEmb consistently outperforms strong baselines on different table annotation tasks. Source code and datasets are available at https://github.com/hoseinzadeehsan/TabEmb