@inproceedings{ilgen-etal-2026-vaxscope,
title = "{V}ax{S}cope: Document-Level Structured Evidence Extraction from Immunization Systematic Reviews",
author = "Ilgen, Bahar and
Awotoro, Ebenezer and
Hattab, Georges",
editor = "Demner-Fushman, Dina and
Ananiadou, Sophia and
Roberts, Kirk and
Tsujii, Junichi",
booktitle = "{B}io{NLP} 2026",
month = jul,
year = "2026",
address = "San Diego, California",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.bionlp-1.69/",
pages = "853--863",
ISBN = "979-8-89176-434-7",
abstract = "Systematic reviews are fundamental to evidence-based medicine, but the clinical evidence they contain is primarily expressed in unstructured text, making large-scale extraction and reuse difficult. Existing biomedical NLP methods have achieved strong performance on span-level extraction from clinical trials and abstracts; however, these approaches are insufficient for systematic reviews, where evidence is often distributed across multiple studies, sentences, and sections and must be aggregated into normalized document-level attributes. We introduce VaxScope, a benchmark dataset for document-level structured evidence extraction from immunization-related systematic reviews. VaxScope is constructed through an expert-guided semi-automatic annotation pipeline that combines automatic candidate generation with domain expert validation to ensure consistency and annotation quality. We formalize the task as document-level structured extraction, where target labels are defined at the review level and require aggregating evidence beyond isolated textual spans. We further establish baselines for document-level structured extraction using abstract-level input representations and evaluate how access to evidence-grounded contextual input improves performance over abstract-only settings. Baseline experiments show that PubMedBERT achieves the best overall performance (Avg F1: 0.850), with evidence-grounded input improving performance particularly for fields requiring distributed contextual reasoning."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ilgen-etal-2026-vaxscope">
<titleInfo>
<title>VaxScope: Document-Level Structured Evidence Extraction from Immunization Systematic Reviews</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bahar</namePart>
<namePart type="family">Ilgen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ebenezer</namePart>
<namePart type="family">Awotoro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georges</namePart>
<namePart type="family">Hattab</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>BioNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Demner-Fushman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kirk</namePart>
<namePart type="family">Roberts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junichi</namePart>
<namePart type="family">Tsujii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-434-7</identifier>
</relatedItem>
<abstract>Systematic reviews are fundamental to evidence-based medicine, but the clinical evidence they contain is primarily expressed in unstructured text, making large-scale extraction and reuse difficult. Existing biomedical NLP methods have achieved strong performance on span-level extraction from clinical trials and abstracts; however, these approaches are insufficient for systematic reviews, where evidence is often distributed across multiple studies, sentences, and sections and must be aggregated into normalized document-level attributes. We introduce VaxScope, a benchmark dataset for document-level structured evidence extraction from immunization-related systematic reviews. VaxScope is constructed through an expert-guided semi-automatic annotation pipeline that combines automatic candidate generation with domain expert validation to ensure consistency and annotation quality. We formalize the task as document-level structured extraction, where target labels are defined at the review level and require aggregating evidence beyond isolated textual spans. We further establish baselines for document-level structured extraction using abstract-level input representations and evaluate how access to evidence-grounded contextual input improves performance over abstract-only settings. Baseline experiments show that PubMedBERT achieves the best overall performance (Avg F1: 0.850), with evidence-grounded input improving performance particularly for fields requiring distributed contextual reasoning.</abstract>
<identifier type="citekey">ilgen-etal-2026-vaxscope</identifier>
<location>
<url>https://aclanthology.org/2026.bionlp-1.69/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>853</start>
<end>863</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T VaxScope: Document-Level Structured Evidence Extraction from Immunization Systematic Reviews
%A Ilgen, Bahar
%A Awotoro, Ebenezer
%A Hattab, Georges
%Y Demner-Fushman, Dina
%Y Ananiadou, Sophia
%Y Roberts, Kirk
%Y Tsujii, Junichi
%S BioNLP 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California
%@ 979-8-89176-434-7
%F ilgen-etal-2026-vaxscope
%X Systematic reviews are fundamental to evidence-based medicine, but the clinical evidence they contain is primarily expressed in unstructured text, making large-scale extraction and reuse difficult. Existing biomedical NLP methods have achieved strong performance on span-level extraction from clinical trials and abstracts; however, these approaches are insufficient for systematic reviews, where evidence is often distributed across multiple studies, sentences, and sections and must be aggregated into normalized document-level attributes. We introduce VaxScope, a benchmark dataset for document-level structured evidence extraction from immunization-related systematic reviews. VaxScope is constructed through an expert-guided semi-automatic annotation pipeline that combines automatic candidate generation with domain expert validation to ensure consistency and annotation quality. We formalize the task as document-level structured extraction, where target labels are defined at the review level and require aggregating evidence beyond isolated textual spans. We further establish baselines for document-level structured extraction using abstract-level input representations and evaluate how access to evidence-grounded contextual input improves performance over abstract-only settings. Baseline experiments show that PubMedBERT achieves the best overall performance (Avg F1: 0.850), with evidence-grounded input improving performance particularly for fields requiring distributed contextual reasoning.
%U https://aclanthology.org/2026.bionlp-1.69/
%P 853-863
Markdown (Informal)
[VaxScope: Document-Level Structured Evidence Extraction from Immunization Systematic Reviews](https://aclanthology.org/2026.bionlp-1.69/) (Ilgen et al., BioNLP 2026)
ACL