@inproceedings{burns-etal-2021-profiling,
title = "Profiling of Intertextuality in {L}atin Literature Using Word Embeddings",
author = "Burns, Patrick J. and
Brofos, James A. and
Li, Kyle and
Chaudhuri, Pramit and
Dexter, Joseph P.",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.389",
doi = "10.18653/v1/2021.naacl-main.389",
pages = "4900--4907",
abstract = "Identifying intertextual relationships between authors is of central importance to the study of literature. We report an empirical analysis of intertextuality in classical Latin literature using word embedding models. To enable quantitative evaluation of intertextual search methods, we curate a new dataset of 945 known parallels drawn from traditional scholarship on Latin epic poetry. We train an optimized word2vec model on a large corpus of lemmatized Latin, which achieves state-of-the-art performance for synonym detection and outperforms a widely used lexical method for intertextual search. We then demonstrate that training embeddings on very small corpora can capture salient aspects of literary style and apply this approach to replicate a previous intertextual study of the Roman historian Livy, which relied on hand-crafted stylometric features. Our results advance the development of core computational resources for a major premodern language and highlight a productive avenue for cross-disciplinary collaboration between the study of literature and NLP.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="burns-etal-2021-profiling">
<titleInfo>
<title>Profiling of Intertextuality in Latin Literature Using Word Embeddings</title>
</titleInfo>
<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">James</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Brofos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyle</namePart>
<namePart type="family">Li</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>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="family">Toutanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Zettlemoyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iz</namePart>
<namePart type="family">Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichao</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Identifying intertextual relationships between authors is of central importance to the study of literature. We report an empirical analysis of intertextuality in classical Latin literature using word embedding models. To enable quantitative evaluation of intertextual search methods, we curate a new dataset of 945 known parallels drawn from traditional scholarship on Latin epic poetry. We train an optimized word2vec model on a large corpus of lemmatized Latin, which achieves state-of-the-art performance for synonym detection and outperforms a widely used lexical method for intertextual search. We then demonstrate that training embeddings on very small corpora can capture salient aspects of literary style and apply this approach to replicate a previous intertextual study of the Roman historian Livy, which relied on hand-crafted stylometric features. Our results advance the development of core computational resources for a major premodern language and highlight a productive avenue for cross-disciplinary collaboration between the study of literature and NLP.</abstract>
<identifier type="citekey">burns-etal-2021-profiling</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.389</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.389</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>4900</start>
<end>4907</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Profiling of Intertextuality in Latin Literature Using Word Embeddings
%A Burns, Patrick J.
%A Brofos, James A.
%A Li, Kyle
%A Chaudhuri, Pramit
%A Dexter, Joseph P.
%Y Toutanova, Kristina
%Y Rumshisky, Anna
%Y Zettlemoyer, Luke
%Y Hakkani-Tur, Dilek
%Y Beltagy, Iz
%Y Bethard, Steven
%Y Cotterell, Ryan
%Y Chakraborty, Tanmoy
%Y Zhou, Yichao
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F burns-etal-2021-profiling
%X Identifying intertextual relationships between authors is of central importance to the study of literature. We report an empirical analysis of intertextuality in classical Latin literature using word embedding models. To enable quantitative evaluation of intertextual search methods, we curate a new dataset of 945 known parallels drawn from traditional scholarship on Latin epic poetry. We train an optimized word2vec model on a large corpus of lemmatized Latin, which achieves state-of-the-art performance for synonym detection and outperforms a widely used lexical method for intertextual search. We then demonstrate that training embeddings on very small corpora can capture salient aspects of literary style and apply this approach to replicate a previous intertextual study of the Roman historian Livy, which relied on hand-crafted stylometric features. Our results advance the development of core computational resources for a major premodern language and highlight a productive avenue for cross-disciplinary collaboration between the study of literature and NLP.
%R 10.18653/v1/2021.naacl-main.389
%U https://aclanthology.org/2021.naacl-main.389
%U https://doi.org/10.18653/v1/2021.naacl-main.389
%P 4900-4907
Markdown (Informal)
[Profiling of Intertextuality in Latin Literature Using Word Embeddings](https://aclanthology.org/2021.naacl-main.389) (Burns et al., NAACL 2021)
ACL
- Patrick J. Burns, James A. Brofos, Kyle Li, Pramit Chaudhuri, and Joseph P. Dexter. 2021. Profiling of Intertextuality in Latin Literature Using Word Embeddings. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4900–4907, Online. Association for Computational Linguistics.