@inproceedings{van-cranenburgh-van-den-berg-2023-direct,
title = "Direct Speech Quote Attribution for {D}utch Literature",
author = "Van Cranenburgh, Andreas and
Van Den Berg, Frank",
editor = "Degaetano-Ortlieb, Stefania and
Kazantseva, Anna and
Reiter, Nils and
Szpakowicz, Stan",
booktitle = "Proceedings of the 7th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.latechclfl-1.6",
doi = "10.18653/v1/2023.latechclfl-1.6",
pages = "45--62",
abstract = "We present a dataset and system for quote attribution in Dutch literature. The system is implemented as a neural module in an existing NLP pipeline for Dutch literature (dutchcoref; van Cranenburgh, 2019). Our contributions are as follows. First, we provide guidelines for Dutch quote attribution and annotate 3,056 quotes in fragments of 42 Dutch literary novels, both contemporary and classic. Second, we present three neural quote attribution classifiers, optimizing for precision, recall, and F1. Third, we perform an evaluation and analysis of quote attribution performance, showing that in particular, quotes with an implicit speaker are challenging, and that such quotes are prevalent in contemporary fiction (57{\%}, compared to 32{\%} for classic novels). On the task of quote attribution, we achieve an improvement of 8.0{\%} F1 points on contemporary fiction and 1.9{\%} F1 points on classic novels. Code, data, and models are available at \url{https://github.com/anonymized/repository}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="van-cranenburgh-van-den-berg-2023-direct">
<titleInfo>
<title>Direct Speech Quote Attribution for Dutch Literature</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Van Cranenburgh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frank</namePart>
<namePart type="family">Van Den Berg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 7th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stefania</namePart>
<namePart type="family">Degaetano-Ortlieb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Kazantseva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nils</namePart>
<namePart type="family">Reiter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stan</namePart>
<namePart type="family">Szpakowicz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a dataset and system for quote attribution in Dutch literature. The system is implemented as a neural module in an existing NLP pipeline for Dutch literature (dutchcoref; van Cranenburgh, 2019). Our contributions are as follows. First, we provide guidelines for Dutch quote attribution and annotate 3,056 quotes in fragments of 42 Dutch literary novels, both contemporary and classic. Second, we present three neural quote attribution classifiers, optimizing for precision, recall, and F1. Third, we perform an evaluation and analysis of quote attribution performance, showing that in particular, quotes with an implicit speaker are challenging, and that such quotes are prevalent in contemporary fiction (57%, compared to 32% for classic novels). On the task of quote attribution, we achieve an improvement of 8.0% F1 points on contemporary fiction and 1.9% F1 points on classic novels. Code, data, and models are available at https://github.com/anonymized/repository.</abstract>
<identifier type="citekey">van-cranenburgh-van-den-berg-2023-direct</identifier>
<identifier type="doi">10.18653/v1/2023.latechclfl-1.6</identifier>
<location>
<url>https://aclanthology.org/2023.latechclfl-1.6</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>45</start>
<end>62</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Direct Speech Quote Attribution for Dutch Literature
%A Van Cranenburgh, Andreas
%A Van Den Berg, Frank
%Y Degaetano-Ortlieb, Stefania
%Y Kazantseva, Anna
%Y Reiter, Nils
%Y Szpakowicz, Stan
%S Proceedings of the 7th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F van-cranenburgh-van-den-berg-2023-direct
%X We present a dataset and system for quote attribution in Dutch literature. The system is implemented as a neural module in an existing NLP pipeline for Dutch literature (dutchcoref; van Cranenburgh, 2019). Our contributions are as follows. First, we provide guidelines for Dutch quote attribution and annotate 3,056 quotes in fragments of 42 Dutch literary novels, both contemporary and classic. Second, we present three neural quote attribution classifiers, optimizing for precision, recall, and F1. Third, we perform an evaluation and analysis of quote attribution performance, showing that in particular, quotes with an implicit speaker are challenging, and that such quotes are prevalent in contemporary fiction (57%, compared to 32% for classic novels). On the task of quote attribution, we achieve an improvement of 8.0% F1 points on contemporary fiction and 1.9% F1 points on classic novels. Code, data, and models are available at https://github.com/anonymized/repository.
%R 10.18653/v1/2023.latechclfl-1.6
%U https://aclanthology.org/2023.latechclfl-1.6
%U https://doi.org/10.18653/v1/2023.latechclfl-1.6
%P 45-62
Markdown (Informal)
[Direct Speech Quote Attribution for Dutch Literature](https://aclanthology.org/2023.latechclfl-1.6) (Van Cranenburgh & Van Den Berg, LaTeCHCLfL 2023)
ACL
- Andreas Van Cranenburgh and Frank Van Den Berg. 2023. Direct Speech Quote Attribution for Dutch Literature. In Proceedings of the 7th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature, pages 45–62, Dubrovnik, Croatia. Association for Computational Linguistics.