TabEmb: Joint Semantic-Structure Embedding for Table Annotation

TL;DR

TabEmb introduces a novel approach for table annotation by combining semantic embeddings from LLMs with structural relationship modeling, leading to improved performance over existing linearization-based methods.

Contribution

The paper presents TabEmb, a method that decouples semantic and structural encoding for tables, enhancing annotation accuracy and generalization.

Findings

TabEmb outperforms baseline models on multiple table annotation tasks.

Decoupling semantic and structural modeling improves representation quality.

Graph-based structural modeling enhances the semantic embeddings.

Abstract

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