Annotating and Classifying Direct Speech in Historical Danish and Norwegian Literary Texts

Ali Mohammed Ali Al-Laith; Alexander Conroy; Kirstine Nielsen Degn; Jens Bjerring-Hansen; Daniel Hershcovich

doi:https://hdl.handle.net/10062/107275

Annotating and Classifying Direct Speech in Historical Danish and Norwegian Literary Texts

Ali Mohammed Ali Al-Laith, Alexander Conroy, Kirstine Nielsen Degn, Jens Bjerring-Hansen, Daniel Hershcovich

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

24 Downloads (Pure)

Abstract

Analyzing direct speech in historical literary texts provides insights into character dynamics, narrative style, and discourse patterns. In late 19th century Danish and Norwegian fiction direct speech
reflects characters’ social and geographical backgrounds. However, inconsistent
typographic conventions in Scandinavian
literature complicate computational methods for distinguishing direct speech from
other narrative elements. To address this,
we introduce an annotated dataset from the
MeMo corpus, capturing speech markers
and tags in Danish and Norwegian novels.
We evaluate pre-trained language models
for classifying direct speech, with results
showing that a Danish Foundation Model
(DFM), trained on extensive Danish data,
has the highest performance. Finally, we
conduct a classifier-assisted quantitative
corpus analysis and find a downward trend
in the prevalence of speech over time.

Original language	English
Title of host publication	Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025
Editors	Sara Stymne, Richard Johansson
Publisher	University of Tartu Library
Publication date	2025
Pages	1-7
ISBN (Electronic)	978-9908-53-109-0
DOIs	https://doi.org/https://hdl.handle.net/10062/107275
Publication status	Published - 2025
Event	25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies - Tallinn, Estonia Duration: 3 Mar 2025 → 4 Mar 2025

Conference

Conference	25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies
Country/Territory	Estonia
City	Tallinn
Period	03/03/2025 → 04/03/2025

Series	NEALT (Northern European Association of Language Technology) Proceedings Series
Volume	57
ISSN	1736-6305

Access to Document

https://hdl.handle.net/10062/107275Licence: CC BY-NC-ND

FulltextFinal published version, 61.4 MBLicence: CC BY-NC-ND

Library access?

Check availability at the Royal Danish Library

Cite this

Al-Laith, A. M. A., Conroy, A., Degn, K. N., Bjerring-Hansen, J., & Hershcovich, D. (2025). Annotating and Classifying Direct Speech in Historical Danish and Norwegian Literary Texts. In S. Stymne, & R. Johansson (Eds.), Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025 (pp. 1-7). University of Tartu Library. https://doi.org/https://hdl.handle.net/10062/107275

Annotating and Classifying Direct Speech in Historical Danish and Norwegian Literary Texts. / Al-Laith, Ali Mohammed Ali ; Conroy, Alexander ; Degn, Kirstine Nielsen et al.
Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025. ed. / Sara Stymne; Richard Johansson. University of Tartu Library, 2025. p. 1-7 (NEALT (Northern European Association of Language Technology) Proceedings Series, Vol. 57).

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Al-Laith, AMA , Conroy, A , Degn, KN , Bjerring-Hansen, J & Hershcovich, D 2025, Annotating and Classifying Direct Speech in Historical Danish and Norwegian Literary Texts. in S Stymne & R Johansson (eds), Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025. University of Tartu Library, NEALT (Northern European Association of Language Technology) Proceedings Series, vol. 57, pp. 1-7, 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies, Tallinn, Estonia, 03/03/2025. https://doi.org/https://hdl.handle.net/10062/107275

Al-Laith AMA , Conroy A , Degn KN , Bjerring-Hansen J , Hershcovich D. Annotating and Classifying Direct Speech in Historical Danish and Norwegian Literary Texts. In Stymne S, Johansson R, editors, Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025. University of Tartu Library. 2025. p. 1-7. (NEALT (Northern European Association of Language Technology) Proceedings Series, Vol. 57). doi: https://hdl.handle.net/10062/107275

Al-Laith, Ali Mohammed Ali ; Conroy, Alexander ; Degn, Kirstine Nielsen et al. / Annotating and Classifying Direct Speech in Historical Danish and Norwegian Literary Texts. Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025. editor / Sara Stymne ; Richard Johansson. University of Tartu Library, 2025. pp. 1-7 (NEALT (Northern European Association of Language Technology) Proceedings Series, Vol. 57).

@inproceedings{e06c41656ae84e8abec62ba9203b2aa8,

title = "Annotating and Classifying Direct Speech in Historical Danish and Norwegian Literary Texts",

abstract = "Analyzing direct speech in historical literary texts provides insights into character dynamics, narrative style, and discourse patterns. In late 19th century Danish and Norwegian fiction direct speechreflects characters{\textquoteright} social and geographical backgrounds. However, inconsistenttypographic conventions in Scandinavianliterature complicate computational methods for distinguishing direct speech fromother narrative elements. To address this,we introduce an annotated dataset from theMeMo corpus, capturing speech markersand tags in Danish and Norwegian novels.We evaluate pre-trained language modelsfor classifying direct speech, with resultsshowing that a Danish Foundation Model(DFM), trained on extensive Danish data,has the highest performance. Finally, weconduct a classifier-assisted quantitativecorpus analysis and find a downward trendin the prevalence of speech over time.",

author = "Al-Laith, {Ali Mohammed Ali} and Alexander Conroy and Degn, {Kirstine Nielsen} and Jens Bjerring-Hansen and Daniel Hershcovich",

year = "2025",

doi = "https://hdl.handle.net/10062/107275",

language = "English",

series = "NEALT (Northern European Association of Language Technology) Proceedings Series",

pages = "1--7",

editor = "Sara Stymne and Richard Johansson",

booktitle = "Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025",

publisher = "University of Tartu Library",

note = "25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies ; Conference date: 03-03-2025 Through 04-03-2025",

}

TY - GEN

T1 - Annotating and Classifying Direct Speech in Historical Danish and Norwegian Literary Texts

AU - Al-Laith, Ali Mohammed Ali

AU - Conroy, Alexander

AU - Degn, Kirstine Nielsen

AU - Bjerring-Hansen, Jens

AU - Hershcovich, Daniel

PY - 2025

Y1 - 2025

N2 - Analyzing direct speech in historical literary texts provides insights into character dynamics, narrative style, and discourse patterns. In late 19th century Danish and Norwegian fiction direct speechreflects characters’ social and geographical backgrounds. However, inconsistenttypographic conventions in Scandinavianliterature complicate computational methods for distinguishing direct speech fromother narrative elements. To address this,we introduce an annotated dataset from theMeMo corpus, capturing speech markersand tags in Danish and Norwegian novels.We evaluate pre-trained language modelsfor classifying direct speech, with resultsshowing that a Danish Foundation Model(DFM), trained on extensive Danish data,has the highest performance. Finally, weconduct a classifier-assisted quantitativecorpus analysis and find a downward trendin the prevalence of speech over time.

AB - Analyzing direct speech in historical literary texts provides insights into character dynamics, narrative style, and discourse patterns. In late 19th century Danish and Norwegian fiction direct speechreflects characters’ social and geographical backgrounds. However, inconsistenttypographic conventions in Scandinavianliterature complicate computational methods for distinguishing direct speech fromother narrative elements. To address this,we introduce an annotated dataset from theMeMo corpus, capturing speech markersand tags in Danish and Norwegian novels.We evaluate pre-trained language modelsfor classifying direct speech, with resultsshowing that a Danish Foundation Model(DFM), trained on extensive Danish data,has the highest performance. Finally, weconduct a classifier-assisted quantitativecorpus analysis and find a downward trendin the prevalence of speech over time.

U2 - https://hdl.handle.net/10062/107275

DO - https://hdl.handle.net/10062/107275

M3 - Article in proceedings

T3 - NEALT (Northern European Association of Language Technology) Proceedings Series

SP - 1

EP - 7

BT - Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025

A2 - Stymne, Sara

A2 - Johansson, Richard

PB - University of Tartu Library

T2 - 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies

Y2 - 3 March 2025 through 4 March 2025

ER -