@inproceedings{zheng-li-2026-tracer,
title = "{TRACER}: An Information Entropy-Grounded Framework for Efficient Large-table Semantic Annotation",
author = "Zheng, Miaoqin and
Li, Shuangyin",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.1137/",
pages = "26088--26097",
ISBN = "979-8-89176-459-0",
abstract = "Large-table semantic annotation aims to assign ontology-grounded semantic labels to columns and column pairs in large relational tables, while considering the efficiency bottleneck caused by the increasing scale of table contexts. However, as relational tables continue to grow in scale, existing methods face a critical effectiveness{--}efficiency trade-off: directly modeling the full table preserves rich context but introduces substantial computational overhead, while aggressive filtering may discard useful semantic cues. To address this issue, we propose TRACER, an information entropy-grounded framework for efficient large-table semantic annotation. TRACER ranks table rows according to ontology-related semantic uncertainty and constructs compact evidence-oriented contexts through hybrid compression, enabling a lightweight semantic reader to perform column type and column property annotation efficiently. From an information-theoretic perspective, TRACER formulates large-table compression as a conditional entropy minimization problem, providing a principled basis for preserving key semantic evidence while filtering redundant information. Experiments on several benchmarks show that TRACER achieves a strong balance between annotation effectiveness and inference efficiency compared with task-specific and large language model baselines. The source code and data are available at https://anonymous.4open.science/r/TRACER-4884."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zheng-li-2026-tracer">
<titleInfo>
<title>TRACER: An Information Entropy-Grounded Framework for Efficient Large-table Semantic Annotation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Miaoqin</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuangyin</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Large-table semantic annotation aims to assign ontology-grounded semantic labels to columns and column pairs in large relational tables, while considering the efficiency bottleneck caused by the increasing scale of table contexts. However, as relational tables continue to grow in scale, existing methods face a critical effectiveness–efficiency trade-off: directly modeling the full table preserves rich context but introduces substantial computational overhead, while aggressive filtering may discard useful semantic cues. To address this issue, we propose TRACER, an information entropy-grounded framework for efficient large-table semantic annotation. TRACER ranks table rows according to ontology-related semantic uncertainty and constructs compact evidence-oriented contexts through hybrid compression, enabling a lightweight semantic reader to perform column type and column property annotation efficiently. From an information-theoretic perspective, TRACER formulates large-table compression as a conditional entropy minimization problem, providing a principled basis for preserving key semantic evidence while filtering redundant information. Experiments on several benchmarks show that TRACER achieves a strong balance between annotation effectiveness and inference efficiency compared with task-specific and large language model baselines. The source code and data are available at https://anonymous.4open.science/r/TRACER-4884.</abstract>
<identifier type="citekey">zheng-li-2026-tracer</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.1137/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>26088</start>
<end>26097</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TRACER: An Information Entropy-Grounded Framework for Efficient Large-table Semantic Annotation
%A Zheng, Miaoqin
%A Li, Shuangyin
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F zheng-li-2026-tracer
%X Large-table semantic annotation aims to assign ontology-grounded semantic labels to columns and column pairs in large relational tables, while considering the efficiency bottleneck caused by the increasing scale of table contexts. However, as relational tables continue to grow in scale, existing methods face a critical effectiveness–efficiency trade-off: directly modeling the full table preserves rich context but introduces substantial computational overhead, while aggressive filtering may discard useful semantic cues. To address this issue, we propose TRACER, an information entropy-grounded framework for efficient large-table semantic annotation. TRACER ranks table rows according to ontology-related semantic uncertainty and constructs compact evidence-oriented contexts through hybrid compression, enabling a lightweight semantic reader to perform column type and column property annotation efficiently. From an information-theoretic perspective, TRACER formulates large-table compression as a conditional entropy minimization problem, providing a principled basis for preserving key semantic evidence while filtering redundant information. Experiments on several benchmarks show that TRACER achieves a strong balance between annotation effectiveness and inference efficiency compared with task-specific and large language model baselines. The source code and data are available at https://anonymous.4open.science/r/TRACER-4884.
%U https://aclanthology.org/2026.emnlp-main.1137/
%P 26088-26097
Markdown (Informal)
[TRACER: An Information Entropy-Grounded Framework for Efficient Large-table Semantic Annotation](https://aclanthology.org/2026.emnlp-main.1137/) (Zheng & Li, EMNLP 2026)
ACL