Saved in:
Bibliographic Details
Main Authors: Jung, Woojun, Yoon, Susik
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2606.01890
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910280240332800
author Jung, Woojun
Yoon, Susik
author_facet Jung, Woojun
Yoon, Susik
contents Real-world domains often contain heterogeneous tables whose headers vary while their underlying attribute semantics are shared, making it difficult to induce domain-specialized semantics from table-local evidence alone. Existing encoders model parts of this problem, but often underuse column-level value distributions and apply uniform objectives across attributes with different semantic roles. We propose NAVI, a segment-centric pretraining framework that treats each header-value pair as the unit for aggregating schema-level structural evidence and column-level distributional evidence. We realize this design through Masked Segment Modeling and Entropy-driven Segment Alignment, which jointly enforce structured header-value coupling and semantic alignment across stable and instance-specific attributes. Experiments on heterogeneous in-domain tables show improved reconstruction, semantic consistency, and downstream utility across evaluation settings overall.
format Preprint
id arxiv_https___arxiv_org_abs_2606_01890
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Segment-driven Structural Induction and Semantic Alignment for Heterogeneous Tabular Representation
Jung, Woojun
Yoon, Susik
Machine Learning
Real-world domains often contain heterogeneous tables whose headers vary while their underlying attribute semantics are shared, making it difficult to induce domain-specialized semantics from table-local evidence alone. Existing encoders model parts of this problem, but often underuse column-level value distributions and apply uniform objectives across attributes with different semantic roles. We propose NAVI, a segment-centric pretraining framework that treats each header-value pair as the unit for aggregating schema-level structural evidence and column-level distributional evidence. We realize this design through Masked Segment Modeling and Entropy-driven Segment Alignment, which jointly enforce structured header-value coupling and semantic alignment across stable and instance-specific attributes. Experiments on heterogeneous in-domain tables show improved reconstruction, semantic consistency, and downstream utility across evaluation settings overall.
title Segment-driven Structural Induction and Semantic Alignment for Heterogeneous Tabular Representation
topic Machine Learning
url https://arxiv.org/abs/2606.01890