@inproceedings{pavlopoulos-etal-2024-holm-analyzing,
title = "{H}o{LM}: Analyzing the Linguistic Unexpectedness in {H}omeric Poetry",
author = "Pavlopoulos, John and
Sandell, Ryan and
Konstantinidou, Maria and
Bozzone, Chiara",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.715",
pages = "8166--8172",
abstract = "The authorship of the Homeric poems has been a matter of debate for centuries. Computational approaches such as language modeling exist that can aid experts in making crucial headway. We observe, however, that such work has, thus far, only been carried out at the level of lengthier excerpts, but not individual verses, the level at which most suspected interpolations occur. We address this weakness by presenting a corpus of Homeric verses, each complemented with a score quantifying linguistic unexpectedness based on Perplexity. We assess the nature of these scores by exploring their correlation with named entities, the frequency of character n-grams, and (inverse) word frequency, revealing robust correlations with the latter two. This apparent bias can be partly overcome by simply dividing scores for unexpectedness by the maximum term frequency per verse.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pavlopoulos-etal-2024-holm-analyzing">
<titleInfo>
<title>HoLM: Analyzing the Linguistic Unexpectedness in Homeric Poetry</title>
</titleInfo>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Pavlopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Sandell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Konstantinidou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chiara</namePart>
<namePart type="family">Bozzone</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The authorship of the Homeric poems has been a matter of debate for centuries. Computational approaches such as language modeling exist that can aid experts in making crucial headway. We observe, however, that such work has, thus far, only been carried out at the level of lengthier excerpts, but not individual verses, the level at which most suspected interpolations occur. We address this weakness by presenting a corpus of Homeric verses, each complemented with a score quantifying linguistic unexpectedness based on Perplexity. We assess the nature of these scores by exploring their correlation with named entities, the frequency of character n-grams, and (inverse) word frequency, revealing robust correlations with the latter two. This apparent bias can be partly overcome by simply dividing scores for unexpectedness by the maximum term frequency per verse.</abstract>
<identifier type="citekey">pavlopoulos-etal-2024-holm-analyzing</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.715</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>8166</start>
<end>8172</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HoLM: Analyzing the Linguistic Unexpectedness in Homeric Poetry
%A Pavlopoulos, John
%A Sandell, Ryan
%A Konstantinidou, Maria
%A Bozzone, Chiara
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F pavlopoulos-etal-2024-holm-analyzing
%X The authorship of the Homeric poems has been a matter of debate for centuries. Computational approaches such as language modeling exist that can aid experts in making crucial headway. We observe, however, that such work has, thus far, only been carried out at the level of lengthier excerpts, but not individual verses, the level at which most suspected interpolations occur. We address this weakness by presenting a corpus of Homeric verses, each complemented with a score quantifying linguistic unexpectedness based on Perplexity. We assess the nature of these scores by exploring their correlation with named entities, the frequency of character n-grams, and (inverse) word frequency, revealing robust correlations with the latter two. This apparent bias can be partly overcome by simply dividing scores for unexpectedness by the maximum term frequency per verse.
%U https://aclanthology.org/2024.lrec-main.715
%P 8166-8172
Markdown (Informal)
[HoLM: Analyzing the Linguistic Unexpectedness in Homeric Poetry](https://aclanthology.org/2024.lrec-main.715) (Pavlopoulos et al., LREC-COLING 2024)
ACL
- John Pavlopoulos, Ryan Sandell, Maria Konstantinidou, and Chiara Bozzone. 2024. HoLM: Analyzing the Linguistic Unexpectedness in Homeric Poetry. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 8166–8172, Torino, Italia. ELRA and ICCL.