@inproceedings{duran-silva-etal-2026-scientific,
title = "Scientific Article Section Classification ({SASC}) Dataset",
author = "Duran-Silva, Nicolau and
Moreno-Schneider, Julian and
Parra-Rojas, C{\'e}sar and
Rehm, Georg",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.587/",
doi = "10.63317/3rdo9r4az3iy",
pages = "7415--7422",
abstract = "We introduce a novel, publicly available dataset of scientific publications specifically designed to focused on the structural and semantic analysis of their full texts. This collection comprises 4,896 scholarly articles processed using GROBID and self-defined parsers for its segmentation and section parsing. To ensure broad utility and diversity, the dataset includes ({\ensuremath{\approx}}1,000) papers from 4 specialized research areas: Energy, Cancer, Neuroscience, and Transportation, supplemented by an additional {\ensuremath{\approx}}1,000 papers randomly selected from general scientific domains. This dataset is annotated using a newly-defined hierarchical taxonomy comprising 2 levels: the first level contains 9 semantic classes (coarse-grained), while the second level contains 47 semantic classes (fine-grained). All source documents were ethically and legally sourced via OpenAIRE, and the corpus is restricted exclusively to content available under open licenses. License verification was performed through cross-referencing publisher metadata, landing pages, and the Unpaywall database. This curated dataset provides a robust and domain-diverse resource, ideal for developing and evaluating NLP models that require training on hierarchical structure of scientific literature."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="duran-silva-etal-2026-scientific">
<titleInfo>
<title>Scientific Article Section Classification (SASC) Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicolau</namePart>
<namePart type="family">Duran-Silva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julian</namePart>
<namePart type="family">Moreno-Schneider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">César</namePart>
<namePart type="family">Parra-Rojas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</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 the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce a novel, publicly available dataset of scientific publications specifically designed to focused on the structural and semantic analysis of their full texts. This collection comprises 4,896 scholarly articles processed using GROBID and self-defined parsers for its segmentation and section parsing. To ensure broad utility and diversity, the dataset includes (\ensuremath\approx1,000) papers from 4 specialized research areas: Energy, Cancer, Neuroscience, and Transportation, supplemented by an additional \ensuremath\approx1,000 papers randomly selected from general scientific domains. This dataset is annotated using a newly-defined hierarchical taxonomy comprising 2 levels: the first level contains 9 semantic classes (coarse-grained), while the second level contains 47 semantic classes (fine-grained). All source documents were ethically and legally sourced via OpenAIRE, and the corpus is restricted exclusively to content available under open licenses. License verification was performed through cross-referencing publisher metadata, landing pages, and the Unpaywall database. This curated dataset provides a robust and domain-diverse resource, ideal for developing and evaluating NLP models that require training on hierarchical structure of scientific literature.</abstract>
<identifier type="citekey">duran-silva-etal-2026-scientific</identifier>
<identifier type="doi">10.63317/3rdo9r4az3iy</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.587/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>7415</start>
<end>7422</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Scientific Article Section Classification (SASC) Dataset
%A Duran-Silva, Nicolau
%A Moreno-Schneider, Julian
%A Parra-Rojas, César
%A Rehm, Georg
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F duran-silva-etal-2026-scientific
%X We introduce a novel, publicly available dataset of scientific publications specifically designed to focused on the structural and semantic analysis of their full texts. This collection comprises 4,896 scholarly articles processed using GROBID and self-defined parsers for its segmentation and section parsing. To ensure broad utility and diversity, the dataset includes (\ensuremath\approx1,000) papers from 4 specialized research areas: Energy, Cancer, Neuroscience, and Transportation, supplemented by an additional \ensuremath\approx1,000 papers randomly selected from general scientific domains. This dataset is annotated using a newly-defined hierarchical taxonomy comprising 2 levels: the first level contains 9 semantic classes (coarse-grained), while the second level contains 47 semantic classes (fine-grained). All source documents were ethically and legally sourced via OpenAIRE, and the corpus is restricted exclusively to content available under open licenses. License verification was performed through cross-referencing publisher metadata, landing pages, and the Unpaywall database. This curated dataset provides a robust and domain-diverse resource, ideal for developing and evaluating NLP models that require training on hierarchical structure of scientific literature.
%R 10.63317/3rdo9r4az3iy
%U https://aclanthology.org/2026.lrec-1.587/
%U https://doi.org/10.63317/3rdo9r4az3iy
%P 7415-7422
Markdown (Informal)
[Scientific Article Section Classification (SASC) Dataset](https://aclanthology.org/2026.lrec-1.587/) (Duran-Silva et al., LREC 2026)
ACL
- Nicolau Duran-Silva, Julian Moreno-Schneider, César Parra-Rojas, and Georg Rehm. 2026. Scientific Article Section Classification (SASC) Dataset. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 7415–7422, Palma de Mallorca, Spain. ELRA Language Resource Association.