@inproceedings{arnold-etal-2025-advances,
title = "Advances and Challenges in the Automatic Identification of Indirect Quotations in Scholarly Texts and Literary Works",
author = {Arnold, Frederik and
J{\"a}schke, Robert and
Kraut, Philip},
editor = {H{\"a}m{\"a}l{\"a}inen, Mika and
{\"O}hman, Emily and
Bizzoni, Yuri and
Miyagawa, So and
Alnajjar, Khalid},
booktitle = "Proceedings of the 5th International Conference on Natural Language Processing for Digital Humanities",
month = may,
year = "2025",
address = "Albuquerque, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.nlp4dh-1.15/",
doi = "10.18653/v1/2025.nlp4dh-1.15",
pages = "179--190",
ISBN = "979-8-89176-234-3",
abstract = "Literary scholars commonly refer to the interpreted literary work using various types of quotations. Two main categories are direct and indirect quotations. In this work we focus on the automatic identification of two subtypes of indirect quotations: paraphrases and summaries. Our contributions are twofold. First, we present a dataset of scholarly works with annotations of text spans which summarize or paraphrase the interpreted drama and the source of the quotation. Second, we present a two-step approach to solve the task at hand. We found the process of annotating large training corpora very time consuming and therefore leverage GPT-generated summaries to generate training data for our approach."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="arnold-etal-2025-advances">
<titleInfo>
<title>Advances and Challenges in the Automatic Identification of Indirect Quotations in Scholarly Texts and Literary Works</title>
</titleInfo>
<name type="personal">
<namePart type="given">Frederik</namePart>
<namePart type="family">Arnold</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Jäschke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philip</namePart>
<namePart type="family">Kraut</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 5th International Conference on Natural Language Processing for Digital Humanities</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mika</namePart>
<namePart type="family">Hämäläinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emily</namePart>
<namePart type="family">Öhman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuri</namePart>
<namePart type="family">Bizzoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">So</namePart>
<namePart type="family">Miyagawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Alnajjar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-234-3</identifier>
</relatedItem>
<abstract>Literary scholars commonly refer to the interpreted literary work using various types of quotations. Two main categories are direct and indirect quotations. In this work we focus on the automatic identification of two subtypes of indirect quotations: paraphrases and summaries. Our contributions are twofold. First, we present a dataset of scholarly works with annotations of text spans which summarize or paraphrase the interpreted drama and the source of the quotation. Second, we present a two-step approach to solve the task at hand. We found the process of annotating large training corpora very time consuming and therefore leverage GPT-generated summaries to generate training data for our approach.</abstract>
<identifier type="citekey">arnold-etal-2025-advances</identifier>
<identifier type="doi">10.18653/v1/2025.nlp4dh-1.15</identifier>
<location>
<url>https://aclanthology.org/2025.nlp4dh-1.15/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>179</start>
<end>190</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Advances and Challenges in the Automatic Identification of Indirect Quotations in Scholarly Texts and Literary Works
%A Arnold, Frederik
%A Jäschke, Robert
%A Kraut, Philip
%Y Hämäläinen, Mika
%Y Öhman, Emily
%Y Bizzoni, Yuri
%Y Miyagawa, So
%Y Alnajjar, Khalid
%S Proceedings of the 5th International Conference on Natural Language Processing for Digital Humanities
%D 2025
%8 May
%I Association for Computational Linguistics
%C Albuquerque, USA
%@ 979-8-89176-234-3
%F arnold-etal-2025-advances
%X Literary scholars commonly refer to the interpreted literary work using various types of quotations. Two main categories are direct and indirect quotations. In this work we focus on the automatic identification of two subtypes of indirect quotations: paraphrases and summaries. Our contributions are twofold. First, we present a dataset of scholarly works with annotations of text spans which summarize or paraphrase the interpreted drama and the source of the quotation. Second, we present a two-step approach to solve the task at hand. We found the process of annotating large training corpora very time consuming and therefore leverage GPT-generated summaries to generate training data for our approach.
%R 10.18653/v1/2025.nlp4dh-1.15
%U https://aclanthology.org/2025.nlp4dh-1.15/
%U https://doi.org/10.18653/v1/2025.nlp4dh-1.15
%P 179-190
Markdown (Informal)
[Advances and Challenges in the Automatic Identification of Indirect Quotations in Scholarly Texts and Literary Works](https://aclanthology.org/2025.nlp4dh-1.15/) (Arnold et al., NLP4DH 2025)
ACL