@inproceedings{mourky-etal-2026-unicite,
title = "{U}ni{C}ite: A Dataset and Unified Hierarchical Taxonomy for Multi-Dimensional Citation Analysis",
author = "Mourky, Amina and
Leitner, Elena and
Moreno-Schneider, Julian and
Abu Ahmad, Raia and
Borisova, Ekaterina and
Rehm, Georg",
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-1.28/",
doi = "10.63317/472sud9pm8t5",
pages = "277--288",
abstract = "Research in Citation Context Analysis (CCA) has produced numerous taxonomic schemes that vary from three to 12+ categories, with different granularities and no mappings between frameworks, severely limiting systematic comparison and progress. Despite decades of study, CCA methods have largely relied on fragmented frameworks that treat citation tasks independently, ignoring systematic relationships between function classification, sentiment analysis, and importance assessment. To address these research gaps, we present three integrated contributions. First, we develop UniCite, a two-level taxonomy (six primary functions, 12 subcategories, two orthogonal dimensions) that systematically integrates three existing schemes. Second, we develop a comprehensive dataset of 4,017 citations combining established resources with 1,547 newly extracted citations from 2018-2024 publications, all manually annotated under our unified framework. Third, we demonstrate systematic task relationships through multi-task learning, achieving 21.1{\%} relative improvement in subfunction classification over single-task approaches."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mourky-etal-2026-unicite">
<titleInfo>
<title>UniCite: A Dataset and Unified Hierarchical Taxonomy for Multi-Dimensional Citation Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amina</namePart>
<namePart type="family">Mourky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Leitner</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">Raia</namePart>
<namePart type="family">Abu Ahmad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Borisova</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 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>Research in Citation Context Analysis (CCA) has produced numerous taxonomic schemes that vary from three to 12+ categories, with different granularities and no mappings between frameworks, severely limiting systematic comparison and progress. Despite decades of study, CCA methods have largely relied on fragmented frameworks that treat citation tasks independently, ignoring systematic relationships between function classification, sentiment analysis, and importance assessment. To address these research gaps, we present three integrated contributions. First, we develop UniCite, a two-level taxonomy (six primary functions, 12 subcategories, two orthogonal dimensions) that systematically integrates three existing schemes. Second, we develop a comprehensive dataset of 4,017 citations combining established resources with 1,547 newly extracted citations from 2018-2024 publications, all manually annotated under our unified framework. Third, we demonstrate systematic task relationships through multi-task learning, achieving 21.1% relative improvement in subfunction classification over single-task approaches.</abstract>
<identifier type="citekey">mourky-etal-2026-unicite</identifier>
<identifier type="doi">10.63317/472sud9pm8t5</identifier>
<location>
<url>https://aclanthology.org/2026.nslp-1.28/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>277</start>
<end>288</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UniCite: A Dataset and Unified Hierarchical Taxonomy for Multi-Dimensional Citation Analysis
%A Mourky, Amina
%A Leitner, Elena
%A Moreno-Schneider, Julian
%A Abu Ahmad, Raia
%A Borisova, Ekaterina
%A Rehm, Georg
%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 mourky-etal-2026-unicite
%X Research in Citation Context Analysis (CCA) has produced numerous taxonomic schemes that vary from three to 12+ categories, with different granularities and no mappings between frameworks, severely limiting systematic comparison and progress. Despite decades of study, CCA methods have largely relied on fragmented frameworks that treat citation tasks independently, ignoring systematic relationships between function classification, sentiment analysis, and importance assessment. To address these research gaps, we present three integrated contributions. First, we develop UniCite, a two-level taxonomy (six primary functions, 12 subcategories, two orthogonal dimensions) that systematically integrates three existing schemes. Second, we develop a comprehensive dataset of 4,017 citations combining established resources with 1,547 newly extracted citations from 2018-2024 publications, all manually annotated under our unified framework. Third, we demonstrate systematic task relationships through multi-task learning, achieving 21.1% relative improvement in subfunction classification over single-task approaches.
%R 10.63317/472sud9pm8t5
%U https://aclanthology.org/2026.nslp-1.28/
%U https://doi.org/10.63317/472sud9pm8t5
%P 277-288
Markdown (Informal)
[UniCite: A Dataset and Unified Hierarchical Taxonomy for Multi-Dimensional Citation Analysis](https://aclanthology.org/2026.nslp-1.28/) (Mourky et al., NSLP 2026)
ACL