@inproceedings{schelb-etal-2026-loci,
title = "Loci Similes: A Benchmark for Extracting Intertextualities in {L}atin Literature",
author = "Schelb, Julian and
Wittweiler, Michael and
Revellio, Marie and
Feichtinger, Barbara and
Spitz, Andreas",
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.1224/",
pages = "25899--25924",
ISBN = "979-8-89176-462-0",
abstract = "Tracing connections between historical texts is an important part of intertextual research, enabling scholars to reconstruct the virtual library of a writer and identify the sources influencing their creative process. These intertextual links manifest in diverse forms, ranging from direct verbatim quotations to subtle allusions and paraphrases disguised by morphological variation. Language models offer a promising path forward due to their capability of capturing semantic similarity beyond lexical overlap. However, the development of new methods for this task is held back by the scarcity of standardized benchmarks and easy-to-use datasets. We address this gap by introducing Loci Similes, a benchmark for Latin intertextuality detection comprising a curated dataset of {\textasciitilde}176k text segments and 1,490 expert-verified parallels, including 945 labeled references from an existing dataset. Using this data, we establish baselines for retrieval and classification of intertextualities with both lexical methods and pretrained encoder language models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="schelb-etal-2026-loci">
<titleInfo>
<title>Loci Similes: A Benchmark for Extracting Intertextualities in Latin Literature</title>
</titleInfo>
<name type="personal">
<namePart type="given">Julian</namePart>
<namePart type="family">Schelb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Wittweiler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie</namePart>
<namePart type="family">Revellio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Feichtinger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Spitz</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>Tracing connections between historical texts is an important part of intertextual research, enabling scholars to reconstruct the virtual library of a writer and identify the sources influencing their creative process. These intertextual links manifest in diverse forms, ranging from direct verbatim quotations to subtle allusions and paraphrases disguised by morphological variation. Language models offer a promising path forward due to their capability of capturing semantic similarity beyond lexical overlap. However, the development of new methods for this task is held back by the scarcity of standardized benchmarks and easy-to-use datasets. We address this gap by introducing Loci Similes, a benchmark for Latin intertextuality detection comprising a curated dataset of ~176k text segments and 1,490 expert-verified parallels, including 945 labeled references from an existing dataset. Using this data, we establish baselines for retrieval and classification of intertextualities with both lexical methods and pretrained encoder language models.</abstract>
<identifier type="citekey">schelb-etal-2026-loci</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1224/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>25899</start>
<end>25924</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Loci Similes: A Benchmark for Extracting Intertextualities in Latin Literature
%A Schelb, Julian
%A Wittweiler, Michael
%A Revellio, Marie
%A Feichtinger, Barbara
%A Spitz, Andreas
%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 schelb-etal-2026-loci
%X Tracing connections between historical texts is an important part of intertextual research, enabling scholars to reconstruct the virtual library of a writer and identify the sources influencing their creative process. These intertextual links manifest in diverse forms, ranging from direct verbatim quotations to subtle allusions and paraphrases disguised by morphological variation. Language models offer a promising path forward due to their capability of capturing semantic similarity beyond lexical overlap. However, the development of new methods for this task is held back by the scarcity of standardized benchmarks and easy-to-use datasets. We address this gap by introducing Loci Similes, a benchmark for Latin intertextuality detection comprising a curated dataset of ~176k text segments and 1,490 expert-verified parallels, including 945 labeled references from an existing dataset. Using this data, we establish baselines for retrieval and classification of intertextualities with both lexical methods and pretrained encoder language models.
%U https://aclanthology.org/2026.findings-emnlp.1224/
%P 25899-25924
Markdown (Informal)
[Loci Similes: A Benchmark for Extracting Intertextualities in Latin Literature](https://aclanthology.org/2026.findings-emnlp.1224/) (Schelb et al., Findings 2026)
ACL