@inproceedings{fedchin-etal-2025-acrosticsleuth,
title = "{A}crostic{S}leuth: Probabilistic Identification and Ranking of Acrostics in Multilingual Corpora",
author = "Fedchin, Aleksandr and
Cooperman, Isabel and
Chaudhuri, Pramit and
Dexter, Joseph P.",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-naacl.414/",
doi = "10.18653/v1/2025.findings-naacl.414",
pages = "7430--7437",
ISBN = "979-8-89176-195-7",
abstract = "For centuries, writers have hidden messages as acrostics, in which initial letters of consecutive lines or paragraphs form meaningful words or phrases. Scholars searching for acrostics manually can only focus on a few authors at a time and often favor qualitative arguments about whether a given acrostic is accidental or intentional. Here we describe AcrosticSleuth, a first-of-its-kind approach to identify acrostics automatically and rank them by the probability that the corresponding sequence of characters does not occur by chance. Since acrostics are rare, we formalize the problem as a binary classification task in the presence of extreme class imbalance. To evaluate AcrosticSleuth, we present the Acrostic Identification Dataset (AcrostID), a collection of acrostics from the WikiSource online database. Despite the class imbalance, AcrosticSleuth achieves F1 scores of 0.39, 0.59, and 0.66 on the French, English, and Russian subdomains of WikiSource, respectively. We further demonstrate that AcrosticSleuth can identify previously unknown instances of wordplay in high-profile literary contexts, including the English philosopher Thomas Hobbes' signature in the opening paragraphs of The Elements of Law."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fedchin-etal-2025-acrosticsleuth">
<titleInfo>
<title>AcrosticSleuth: Probabilistic Identification and Ranking of Acrostics in Multilingual Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aleksandr</namePart>
<namePart type="family">Fedchin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabel</namePart>
<namePart type="family">Cooperman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pramit</namePart>
<namePart type="family">Chaudhuri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Dexter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-195-7</identifier>
</relatedItem>
<abstract>For centuries, writers have hidden messages as acrostics, in which initial letters of consecutive lines or paragraphs form meaningful words or phrases. Scholars searching for acrostics manually can only focus on a few authors at a time and often favor qualitative arguments about whether a given acrostic is accidental or intentional. Here we describe AcrosticSleuth, a first-of-its-kind approach to identify acrostics automatically and rank them by the probability that the corresponding sequence of characters does not occur by chance. Since acrostics are rare, we formalize the problem as a binary classification task in the presence of extreme class imbalance. To evaluate AcrosticSleuth, we present the Acrostic Identification Dataset (AcrostID), a collection of acrostics from the WikiSource online database. Despite the class imbalance, AcrosticSleuth achieves F1 scores of 0.39, 0.59, and 0.66 on the French, English, and Russian subdomains of WikiSource, respectively. We further demonstrate that AcrosticSleuth can identify previously unknown instances of wordplay in high-profile literary contexts, including the English philosopher Thomas Hobbes’ signature in the opening paragraphs of The Elements of Law.</abstract>
<identifier type="citekey">fedchin-etal-2025-acrosticsleuth</identifier>
<identifier type="doi">10.18653/v1/2025.findings-naacl.414</identifier>
<location>
<url>https://aclanthology.org/2025.findings-naacl.414/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>7430</start>
<end>7437</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AcrosticSleuth: Probabilistic Identification and Ranking of Acrostics in Multilingual Corpora
%A Fedchin, Aleksandr
%A Cooperman, Isabel
%A Chaudhuri, Pramit
%A Dexter, Joseph P.
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Findings of the Association for Computational Linguistics: NAACL 2025
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-195-7
%F fedchin-etal-2025-acrosticsleuth
%X For centuries, writers have hidden messages as acrostics, in which initial letters of consecutive lines or paragraphs form meaningful words or phrases. Scholars searching for acrostics manually can only focus on a few authors at a time and often favor qualitative arguments about whether a given acrostic is accidental or intentional. Here we describe AcrosticSleuth, a first-of-its-kind approach to identify acrostics automatically and rank them by the probability that the corresponding sequence of characters does not occur by chance. Since acrostics are rare, we formalize the problem as a binary classification task in the presence of extreme class imbalance. To evaluate AcrosticSleuth, we present the Acrostic Identification Dataset (AcrostID), a collection of acrostics from the WikiSource online database. Despite the class imbalance, AcrosticSleuth achieves F1 scores of 0.39, 0.59, and 0.66 on the French, English, and Russian subdomains of WikiSource, respectively. We further demonstrate that AcrosticSleuth can identify previously unknown instances of wordplay in high-profile literary contexts, including the English philosopher Thomas Hobbes’ signature in the opening paragraphs of The Elements of Law.
%R 10.18653/v1/2025.findings-naacl.414
%U https://aclanthology.org/2025.findings-naacl.414/
%U https://doi.org/10.18653/v1/2025.findings-naacl.414
%P 7430-7437
Markdown (Informal)
[AcrosticSleuth: Probabilistic Identification and Ranking of Acrostics in Multilingual Corpora](https://aclanthology.org/2025.findings-naacl.414/) (Fedchin et al., Findings 2025)
ACL