Direct Speech Quote Attribution for Dutch Literature

Andreas van Cranenburgh; Frank van den Berg

doi:10.18653/v1/2023.latechclfl-1.6

Direct Speech Quote Attribution for Dutch Literature

Andreas van Cranenburgh, Frank van den Berg

Computational Linguistics (CL)

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

1 Citation (Scopus)

108 Downloads (Pure)

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.

Original language	English
Title of host publication	Proceedings of the 7th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature
Editors	Stefania Degaetano-Ortlieb, Anna Kazantseva, Nils Reiter, Stan Szpakowicz
Publisher	Association for Computational Linguistics (ACL)
Pages	45-62
Number of pages	18
DOIs	https://doi.org/10.18653/v1/2023.latechclfl-1.6
Publication status	Published - 2023
Event	7th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature - Dubrovnik, Croatia Duration: 5-May-2023 → 5-May-2023

Conference

Conference	7th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature
Country/Territory	Croatia
City	Dubrovnik
Period	05/05/2023 → 05/05/2023

Access to Document

10.18653/v1/2023.latechclfl-1.6Licence: CC BY

Direct Speech Quote Attribution for Dutch LiteratureFinal publisher's version, 329 KBLicence: CC BY

Handle.net

Persistent link

Cite this

van Cranenburgh, A., & van den Berg, F. (2023). Direct Speech Quote Attribution for Dutch Literature. In S. Degaetano-Ortlieb, A. Kazantseva, N. Reiter, & S. Szpakowicz (Eds.), Proceedings of the 7th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (pp. 45-62). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2023.latechclfl-1.6

van Cranenburgh, Andreas ; van den Berg, Frank. / Direct Speech Quote Attribution for Dutch Literature. Proceedings of the 7th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature. editor / Stefania Degaetano-Ortlieb ; Anna Kazantseva ; Nils Reiter ; Stan Szpakowicz. Association for Computational Linguistics (ACL), 2023. pp. 45-62

@inproceedings{2a1a7cc60f314da1afadf71d2f4049b6,

title = "Direct Speech Quote Attribution for Dutch Literature",

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.",

author = "{van Cranenburgh}, Andreas and {van den Berg}, Frank",

year = "2023",

doi = "10.18653/v1/2023.latechclfl-1.6",

language = "English",

pages = "45--62",

editor = "Stefania Degaetano-Ortlieb and Anna Kazantseva and Nils Reiter and Stan Szpakowicz",

booktitle = "Proceedings of the 7th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature",

publisher = "Association for Computational Linguistics (ACL)",

note = "7th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature ; Conference date: 05-05-2023 Through 05-05-2023",

}

van Cranenburgh, A & van den Berg, F 2023, Direct Speech Quote Attribution for Dutch Literature. in S Degaetano-Ortlieb, A Kazantseva, N Reiter & S Szpakowicz (eds), Proceedings of the 7th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature. Association for Computational Linguistics (ACL), pp. 45-62, 7th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature, Dubrovnik, Croatia, 05/05/2023. https://doi.org/10.18653/v1/2023.latechclfl-1.6

Direct Speech Quote Attribution for Dutch Literature. / van Cranenburgh, Andreas; van den Berg, Frank.
Proceedings of the 7th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature. ed. / Stefania Degaetano-Ortlieb; Anna Kazantseva; Nils Reiter; Stan Szpakowicz. Association for Computational Linguistics (ACL), 2023. p. 45-62.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Direct Speech Quote Attribution for Dutch Literature

AU - van Cranenburgh, Andreas

AU - van den Berg, Frank

PY - 2023

Y1 - 2023

N2 - 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.

AB - 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.

U2 - 10.18653/v1/2023.latechclfl-1.6

DO - 10.18653/v1/2023.latechclfl-1.6

M3 - Conference contribution

SP - 45

EP - 62

BT - Proceedings of the 7th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature

A2 - Degaetano-Ortlieb, Stefania

A2 - Kazantseva, Anna

A2 - Reiter, Nils

A2 - Szpakowicz, Stan

PB - Association for Computational Linguistics (ACL)

T2 - 7th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature

Y2 - 5 May 2023 through 5 May 2023

ER -

van Cranenburgh A, van den Berg F. Direct Speech Quote Attribution for Dutch Literature. In Degaetano-Ortlieb S, Kazantseva A, Reiter N, Szpakowicz S, editors, Proceedings of the 7th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature. Association for Computational Linguistics (ACL). 2023. p. 45-62 doi: 10.18653/v1/2023.latechclfl-1.6

Direct Speech Quote Attribution for Dutch Literature

Abstract

Conference

Access to Document

Handle.net

Fingerprint

Cite this