@inproceedings{xu-etal-2026-obschema,
title = "{O}b{S}chema: From Local Observations to Global Entity Attribute Schemas in Scientific Literature",
author = "Xu, Xueqiang and
Kweon, Wonbin and
Shi, Jimeng and
Tian, Runchu and
Kang, Yunfan and
Hu, Wei and
Wang, Shaowen and
Han, Jiawei",
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.1103/",
pages = "25278--25300",
ISBN = "979-8-89176-459-0",
abstract = "Scientific literature reports fine-grained entity properties, but such knowledge is scattered across papers, expressed with heterogeneous names, and scoped by experimental conditions. Closed-schema extraction requires predefined attribute vocabularies that are hard to enumerate for property-rich scientific entities, while open-schema extraction often yields duplicate and condition-specific attribute labels. We introduce entity-centric attribute schema induction, which constructs a hierarchical type-level attribute schema from a scientific corpus. We propose ObSchema an observation-to-schema framework that extracts local entity-property observations, aggregates corpus-level evidence to identify recurring attributes, and refines them through value-aware merging and adaptive grouping. On two physical science domains, ObSchema consistently outperforms strong LLM-based schema-induction baselines across different backbone models, producing more compact and coherent schemas."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2026-obschema">
<titleInfo>
<title>ObSchema: From Local Observations to Global Entity Attribute Schemas in Scientific Literature</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xueqiang</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wonbin</namePart>
<namePart type="family">Kweon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jimeng</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Runchu</namePart>
<namePart type="family">Tian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunfan</namePart>
<namePart type="family">Kang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shaowen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiawei</namePart>
<namePart type="family">Han</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>Scientific literature reports fine-grained entity properties, but such knowledge is scattered across papers, expressed with heterogeneous names, and scoped by experimental conditions. Closed-schema extraction requires predefined attribute vocabularies that are hard to enumerate for property-rich scientific entities, while open-schema extraction often yields duplicate and condition-specific attribute labels. We introduce entity-centric attribute schema induction, which constructs a hierarchical type-level attribute schema from a scientific corpus. We propose ObSchema an observation-to-schema framework that extracts local entity-property observations, aggregates corpus-level evidence to identify recurring attributes, and refines them through value-aware merging and adaptive grouping. On two physical science domains, ObSchema consistently outperforms strong LLM-based schema-induction baselines across different backbone models, producing more compact and coherent schemas.</abstract>
<identifier type="citekey">xu-etal-2026-obschema</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.1103/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>25278</start>
<end>25300</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ObSchema: From Local Observations to Global Entity Attribute Schemas in Scientific Literature
%A Xu, Xueqiang
%A Kweon, Wonbin
%A Shi, Jimeng
%A Tian, Runchu
%A Kang, Yunfan
%A Hu, Wei
%A Wang, Shaowen
%A Han, Jiawei
%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 xu-etal-2026-obschema
%X Scientific literature reports fine-grained entity properties, but such knowledge is scattered across papers, expressed with heterogeneous names, and scoped by experimental conditions. Closed-schema extraction requires predefined attribute vocabularies that are hard to enumerate for property-rich scientific entities, while open-schema extraction often yields duplicate and condition-specific attribute labels. We introduce entity-centric attribute schema induction, which constructs a hierarchical type-level attribute schema from a scientific corpus. We propose ObSchema an observation-to-schema framework that extracts local entity-property observations, aggregates corpus-level evidence to identify recurring attributes, and refines them through value-aware merging and adaptive grouping. On two physical science domains, ObSchema consistently outperforms strong LLM-based schema-induction baselines across different backbone models, producing more compact and coherent schemas.
%U https://aclanthology.org/2026.emnlp-main.1103/
%P 25278-25300
Markdown (Informal)
[ObSchema: From Local Observations to Global Entity Attribute Schemas in Scientific Literature](https://aclanthology.org/2026.emnlp-main.1103/) (Xu et al., EMNLP 2026)
ACL
- Xueqiang Xu, Wonbin Kweon, Jimeng Shi, Runchu Tian, Yunfan Kang, Wei Hu, Shaowen Wang, and Jiawei Han. 2026. ObSchema: From Local Observations to Global Entity Attribute Schemas in Scientific Literature. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 25278–25300, Budapest, Hungary. Association for Computational Linguistics.