@inproceedings{chen-etal-2024-leveraging,
title = "Leveraging Part-of-Speech Tagging for Enhanced Stylometry of {L}atin Literature",
author = "Chen, Sarah Li and
Burns, Patrick J. and
Bolt, Thomas J. and
Chaudhuri, Pramit and
Dexter, Joseph P.",
editor = "Pavlopoulos, John and
Sommerschield, Thea and
Assael, Yannis and
Gordin, Shai and
Cho, Kyunghyun and
Passarotti, Marco and
Sprugnoli, Rachele and
Liu, Yudong and
Li, Bin and
Anderson, Adam",
booktitle = "Proceedings of the 1st Workshop on Machine Learning for Ancient Languages (ML4AL 2024)",
month = aug,
year = "2024",
address = "Hybrid in Bangkok, Thailand and online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.ml4al-1.24/",
doi = "10.18653/v1/2024.ml4al-1.24",
pages = "251--259",
abstract = "In literary critical applications, stylometry can benefit from hand-curated feature sets capturing various syntactic and rhetorical functions. For premodern languages, calculation of such features is hampered by a lack of adequate computational resources for accurate part-of-speech tagging and semantic disambiguation. This paper reports an evaluation of POS-taggers for Latin and their use in augmenting a hand-curated stylometric feature set. Our experiments show that POS-augmented features not only provide more accurate counts than POS-blind features but also perform better on tasks such as genre classification. In the course of this work we introduce POS n-grams as a feature for Latin stylometry."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2024-leveraging">
<titleInfo>
<title>Leveraging Part-of-Speech Tagging for Enhanced Stylometry of Latin Literature</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sarah</namePart>
<namePart type="given">Li</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="given">J</namePart>
<namePart type="family">Burns</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="given">J</namePart>
<namePart type="family">Bolt</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>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Machine Learning for Ancient Languages (ML4AL 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Pavlopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thea</namePart>
<namePart type="family">Sommerschield</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yannis</namePart>
<namePart type="family">Assael</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shai</namePart>
<namePart type="family">Gordin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyunghyun</namePart>
<namePart type="family">Cho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Passarotti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachele</namePart>
<namePart type="family">Sprugnoli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yudong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bin</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Anderson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hybrid in Bangkok, Thailand and online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In literary critical applications, stylometry can benefit from hand-curated feature sets capturing various syntactic and rhetorical functions. For premodern languages, calculation of such features is hampered by a lack of adequate computational resources for accurate part-of-speech tagging and semantic disambiguation. This paper reports an evaluation of POS-taggers for Latin and their use in augmenting a hand-curated stylometric feature set. Our experiments show that POS-augmented features not only provide more accurate counts than POS-blind features but also perform better on tasks such as genre classification. In the course of this work we introduce POS n-grams as a feature for Latin stylometry.</abstract>
<identifier type="citekey">chen-etal-2024-leveraging</identifier>
<identifier type="doi">10.18653/v1/2024.ml4al-1.24</identifier>
<location>
<url>https://aclanthology.org/2024.ml4al-1.24/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>251</start>
<end>259</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Leveraging Part-of-Speech Tagging for Enhanced Stylometry of Latin Literature
%A Chen, Sarah Li
%A Burns, Patrick J.
%A Bolt, Thomas J.
%A Chaudhuri, Pramit
%A Dexter, Joseph P.
%Y Pavlopoulos, John
%Y Sommerschield, Thea
%Y Assael, Yannis
%Y Gordin, Shai
%Y Cho, Kyunghyun
%Y Passarotti, Marco
%Y Sprugnoli, Rachele
%Y Liu, Yudong
%Y Li, Bin
%Y Anderson, Adam
%S Proceedings of the 1st Workshop on Machine Learning for Ancient Languages (ML4AL 2024)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Hybrid in Bangkok, Thailand and online
%F chen-etal-2024-leveraging
%X In literary critical applications, stylometry can benefit from hand-curated feature sets capturing various syntactic and rhetorical functions. For premodern languages, calculation of such features is hampered by a lack of adequate computational resources for accurate part-of-speech tagging and semantic disambiguation. This paper reports an evaluation of POS-taggers for Latin and their use in augmenting a hand-curated stylometric feature set. Our experiments show that POS-augmented features not only provide more accurate counts than POS-blind features but also perform better on tasks such as genre classification. In the course of this work we introduce POS n-grams as a feature for Latin stylometry.
%R 10.18653/v1/2024.ml4al-1.24
%U https://aclanthology.org/2024.ml4al-1.24/
%U https://doi.org/10.18653/v1/2024.ml4al-1.24
%P 251-259
Markdown (Informal)
[Leveraging Part-of-Speech Tagging for Enhanced Stylometry of Latin Literature](https://aclanthology.org/2024.ml4al-1.24/) (Chen et al., ML4AL 2024)
ACL