@inproceedings{hou-etal-2026-biopie,
title = "{B}io{PIE}: A Biomedical Protocol Information Extraction Dataset for Experiment Understanding",
author = "Hou, Haofei and
Zhao, Shunyi and
Meng, Fanxu and
Yang, Kairui and
Ruan, Lecheng and
Wang, Qining",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.1934/",
pages = "41234--41257",
ISBN = "979-8-89176-462-0",
abstract = "Understanding biomedical experiments provides a foundation for downstream tasks, e.g., laboratory automation, and facilitates effective cross-disciplinary communication. Two challenges, High Information Density (HID) and Multi-Step Reasoning (MSR), pose unique difficulties for precise automatic experimental understanding. Extracting structured knowledge, e.g., Knowledge Graphs (KGs), is an effective approach to address the HID and MSR. However, existing biomedical datasets for structured knowledge Information Extraction (IE) are limited to a general or coarse-grained level, hindering fine-grained experimental understanding. To address this gap, we introduce Biomedical Protocol Information Extraction Dataset (BioPIE), a dataset providing procedure-centric KGs that captures entities, actions, and relations at a scale sufficient for reasoning across biomedical protocols. We evaluate both supervised and LLM-based IE methods on BioPIE to verify its effectiveness, and implement a biomedical question answering system to provide a quantitative illustration of BioPIE{'}s effectiveness for downstream understanding tasks. The experimental results demonstrate improved understanding performance on both the HID and MSR question sets."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hou-etal-2026-biopie">
<titleInfo>
<title>BioPIE: A Biomedical Protocol Information Extraction Dataset for Experiment Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haofei</namePart>
<namePart type="family">Hou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shunyi</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fanxu</namePart>
<namePart type="family">Meng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kairui</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lecheng</namePart>
<namePart type="family">Ruan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qining</namePart>
<namePart type="family">Wang</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>Findings of the Association for Computational Linguistics: EMNLP 2026</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">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Understanding biomedical experiments provides a foundation for downstream tasks, e.g., laboratory automation, and facilitates effective cross-disciplinary communication. Two challenges, High Information Density (HID) and Multi-Step Reasoning (MSR), pose unique difficulties for precise automatic experimental understanding. Extracting structured knowledge, e.g., Knowledge Graphs (KGs), is an effective approach to address the HID and MSR. However, existing biomedical datasets for structured knowledge Information Extraction (IE) are limited to a general or coarse-grained level, hindering fine-grained experimental understanding. To address this gap, we introduce Biomedical Protocol Information Extraction Dataset (BioPIE), a dataset providing procedure-centric KGs that captures entities, actions, and relations at a scale sufficient for reasoning across biomedical protocols. We evaluate both supervised and LLM-based IE methods on BioPIE to verify its effectiveness, and implement a biomedical question answering system to provide a quantitative illustration of BioPIE’s effectiveness for downstream understanding tasks. The experimental results demonstrate improved understanding performance on both the HID and MSR question sets.</abstract>
<identifier type="citekey">hou-etal-2026-biopie</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1934/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>41234</start>
<end>41257</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BioPIE: A Biomedical Protocol Information Extraction Dataset for Experiment Understanding
%A Hou, Haofei
%A Zhao, Shunyi
%A Meng, Fanxu
%A Yang, Kairui
%A Ruan, Lecheng
%A Wang, Qining
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F hou-etal-2026-biopie
%X Understanding biomedical experiments provides a foundation for downstream tasks, e.g., laboratory automation, and facilitates effective cross-disciplinary communication. Two challenges, High Information Density (HID) and Multi-Step Reasoning (MSR), pose unique difficulties for precise automatic experimental understanding. Extracting structured knowledge, e.g., Knowledge Graphs (KGs), is an effective approach to address the HID and MSR. However, existing biomedical datasets for structured knowledge Information Extraction (IE) are limited to a general or coarse-grained level, hindering fine-grained experimental understanding. To address this gap, we introduce Biomedical Protocol Information Extraction Dataset (BioPIE), a dataset providing procedure-centric KGs that captures entities, actions, and relations at a scale sufficient for reasoning across biomedical protocols. We evaluate both supervised and LLM-based IE methods on BioPIE to verify its effectiveness, and implement a biomedical question answering system to provide a quantitative illustration of BioPIE’s effectiveness for downstream understanding tasks. The experimental results demonstrate improved understanding performance on both the HID and MSR question sets.
%U https://aclanthology.org/2026.findings-emnlp.1934/
%P 41234-41257
Markdown (Informal)
[BioPIE: A Biomedical Protocol Information Extraction Dataset for Experiment Understanding](https://aclanthology.org/2026.findings-emnlp.1934/) (Hou et al., Findings 2026)
ACL