@inproceedings{datta-etal-2026-beyond,
title = "Beyond Abstracts: A Biomedical {M}e{SH} Indexing Corpus Incorporating Summarized Methods Sections",
author = "Datta, Sujoy and
Mercer, Robert E. and
Wang, Xindi",
editor = "Rehm, Georg and
Dietze, Stefan and
Dessi, Danilo and
Maynard, Diana and
Schimmler, Sonja",
booktitle = "Proceedings of Natural Scientific Language Processing ({NSLP}) @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.nslp-1.4/",
doi = "10.63317/4iw4aavrxi9o",
pages = "32--43",
abstract = "Automated Medical Subject Heading (MeSH) indexing systems rely predominantly on titles and abstracts, while human indexers at the National Library of Medicine examine full-text articles{---}particularly Methods sections{---}that often contain crucial experimental terminology absent from abstracts. This information asymmetry limits model performance and prevents detection of methodologically-grounded MeSH descriptors. We introduce a novel biomedical MeSH indexing corpus comprising over one million English biomedical articles, each annotated with title, abstract, journal metadata, publication year, expert-curated MeSH terms, and{---}uniquely{---}extractive summaries of Methods sections. Using LLaMA 3 with an iterative re-prompting strategy, we generated high-fidelity summaries. To avoid label leakage, evaluation labels are inferred using journal-specific MeSH frequency profiles rather than gold annotations. This publicly accessible dataset addresses a critical gap in full-text MeSH indexing research. Building upon this resource, we propose an extended multi-channel neural architecture that incorporates Methods-derived representations. Empirical results demonstrate consistent performance gains across both example-based and label-based evaluations, indicating better retrieval of infrequent terms. These findings highlight that procedural knowledge in the Methods section encodes critical semantic cues overlooked by title-abstract only models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="datta-etal-2026-beyond">
<titleInfo>
<title>Beyond Abstracts: A Biomedical MeSH Indexing Corpus Incorporating Summarized Methods Sections</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sujoy</namePart>
<namePart type="family">Datta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="given">E</namePart>
<namePart type="family">Mercer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xindi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of Natural Scientific Language Processing (NSLP) @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Dietze</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danilo</namePart>
<namePart type="family">Dessi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diana</namePart>
<namePart type="family">Maynard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sonja</namePart>
<namePart type="family">Schimmler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automated Medical Subject Heading (MeSH) indexing systems rely predominantly on titles and abstracts, while human indexers at the National Library of Medicine examine full-text articles—particularly Methods sections—that often contain crucial experimental terminology absent from abstracts. This information asymmetry limits model performance and prevents detection of methodologically-grounded MeSH descriptors. We introduce a novel biomedical MeSH indexing corpus comprising over one million English biomedical articles, each annotated with title, abstract, journal metadata, publication year, expert-curated MeSH terms, and—uniquely—extractive summaries of Methods sections. Using LLaMA 3 with an iterative re-prompting strategy, we generated high-fidelity summaries. To avoid label leakage, evaluation labels are inferred using journal-specific MeSH frequency profiles rather than gold annotations. This publicly accessible dataset addresses a critical gap in full-text MeSH indexing research. Building upon this resource, we propose an extended multi-channel neural architecture that incorporates Methods-derived representations. Empirical results demonstrate consistent performance gains across both example-based and label-based evaluations, indicating better retrieval of infrequent terms. These findings highlight that procedural knowledge in the Methods section encodes critical semantic cues overlooked by title-abstract only models.</abstract>
<identifier type="citekey">datta-etal-2026-beyond</identifier>
<identifier type="doi">10.63317/4iw4aavrxi9o</identifier>
<location>
<url>https://aclanthology.org/2026.nslp-1.4/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>32</start>
<end>43</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Beyond Abstracts: A Biomedical MeSH Indexing Corpus Incorporating Summarized Methods Sections
%A Datta, Sujoy
%A Mercer, Robert E.
%A Wang, Xindi
%Y Rehm, Georg
%Y Dietze, Stefan
%Y Dessi, Danilo
%Y Maynard, Diana
%Y Schimmler, Sonja
%S Proceedings of Natural Scientific Language Processing (NSLP) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F datta-etal-2026-beyond
%X Automated Medical Subject Heading (MeSH) indexing systems rely predominantly on titles and abstracts, while human indexers at the National Library of Medicine examine full-text articles—particularly Methods sections—that often contain crucial experimental terminology absent from abstracts. This information asymmetry limits model performance and prevents detection of methodologically-grounded MeSH descriptors. We introduce a novel biomedical MeSH indexing corpus comprising over one million English biomedical articles, each annotated with title, abstract, journal metadata, publication year, expert-curated MeSH terms, and—uniquely—extractive summaries of Methods sections. Using LLaMA 3 with an iterative re-prompting strategy, we generated high-fidelity summaries. To avoid label leakage, evaluation labels are inferred using journal-specific MeSH frequency profiles rather than gold annotations. This publicly accessible dataset addresses a critical gap in full-text MeSH indexing research. Building upon this resource, we propose an extended multi-channel neural architecture that incorporates Methods-derived representations. Empirical results demonstrate consistent performance gains across both example-based and label-based evaluations, indicating better retrieval of infrequent terms. These findings highlight that procedural knowledge in the Methods section encodes critical semantic cues overlooked by title-abstract only models.
%R 10.63317/4iw4aavrxi9o
%U https://aclanthology.org/2026.nslp-1.4/
%U https://doi.org/10.63317/4iw4aavrxi9o
%P 32-43
Markdown (Informal)
[Beyond Abstracts: A Biomedical MeSH Indexing Corpus Incorporating Summarized Methods Sections](https://aclanthology.org/2026.nslp-1.4/) (Datta et al., NSLP 2026)
ACL