@inproceedings{byszuk-etal-2020-detecting,
title = "Detecting Direct Speech in Multilingual Collection of 19th-century Novels",
author = "Byszuk, Joanna and
Wo{\'z}niak, Micha{\l} and
Kestemont, Mike and
Le{\'s}niak, Albert and
{\L}ukasik, Wojciech and
{\v{S}}e{\c{l}}a, Artjoms and
Eder, Maciej",
editor = "Sprugnoli, Rachele and
Passarotti, Marco",
booktitle = "Proceedings of LT4HALA 2020 - 1st Workshop on Language Technologies for Historical and Ancient Languages",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/2020.lt4hala-1.15",
pages = "100--104",
abstract = "Fictional prose can be broadly divided into narrative and discursive forms with direct speech being central to any discourse representation (alongside indirect reported speech and free indirect discourse). This distinction is crucial in digital literary studies and enables interesting forms of narratological or stylistic analysis. The difficulty of automatically detecting direct speech, however, is currently under-estimated. Rule-based systems that work reasonably well for modern languages struggle with (the lack of) typographical conventions in 19th-century literature. While machine learning approaches to sequence modeling can be applied to solve the task, they typically face a severed skewness in the availability of training material, especially for lesser resourced languages. In this paper, we report the result of a multilingual approach to direct speech detection in a diverse corpus of 19th-century fiction in 9 European languages. The proposed method finetunes a transformer architecture with multilingual sentence embedder on a minimal amount of annotated training in each language, and improves performance across languages with ambiguous direct speech marking, in comparison to a carefully constructed regular expression baseline.",
language = "English",
ISBN = "979-10-95546-53-5",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="byszuk-etal-2020-detecting">
<titleInfo>
<title>Detecting Direct Speech in Multilingual Collection of 19th-century Novels</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joanna</namePart>
<namePart type="family">Byszuk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michał</namePart>
<namePart type="family">Woźniak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Kestemont</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Albert</namePart>
<namePart type="family">Leśniak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wojciech</namePart>
<namePart type="family">Łukasik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Artjoms</namePart>
<namePart type="family">Šeļa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maciej</namePart>
<namePart type="family">Eder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of LT4HALA 2020 - 1st Workshop on Language Technologies for Historical and Ancient Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rachele</namePart>
<namePart type="family">Sprugnoli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Passarotti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-53-5</identifier>
</relatedItem>
<abstract>Fictional prose can be broadly divided into narrative and discursive forms with direct speech being central to any discourse representation (alongside indirect reported speech and free indirect discourse). This distinction is crucial in digital literary studies and enables interesting forms of narratological or stylistic analysis. The difficulty of automatically detecting direct speech, however, is currently under-estimated. Rule-based systems that work reasonably well for modern languages struggle with (the lack of) typographical conventions in 19th-century literature. While machine learning approaches to sequence modeling can be applied to solve the task, they typically face a severed skewness in the availability of training material, especially for lesser resourced languages. In this paper, we report the result of a multilingual approach to direct speech detection in a diverse corpus of 19th-century fiction in 9 European languages. The proposed method finetunes a transformer architecture with multilingual sentence embedder on a minimal amount of annotated training in each language, and improves performance across languages with ambiguous direct speech marking, in comparison to a carefully constructed regular expression baseline.</abstract>
<identifier type="citekey">byszuk-etal-2020-detecting</identifier>
<location>
<url>https://aclanthology.org/2020.lt4hala-1.15</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>100</start>
<end>104</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Detecting Direct Speech in Multilingual Collection of 19th-century Novels
%A Byszuk, Joanna
%A Woźniak, Michał
%A Kestemont, Mike
%A Leśniak, Albert
%A Łukasik, Wojciech
%A Šeļa, Artjoms
%A Eder, Maciej
%Y Sprugnoli, Rachele
%Y Passarotti, Marco
%S Proceedings of LT4HALA 2020 - 1st Workshop on Language Technologies for Historical and Ancient Languages
%D 2020
%8 May
%I European Language Resources Association (ELRA)
%C Marseille, France
%@ 979-10-95546-53-5
%G English
%F byszuk-etal-2020-detecting
%X Fictional prose can be broadly divided into narrative and discursive forms with direct speech being central to any discourse representation (alongside indirect reported speech and free indirect discourse). This distinction is crucial in digital literary studies and enables interesting forms of narratological or stylistic analysis. The difficulty of automatically detecting direct speech, however, is currently under-estimated. Rule-based systems that work reasonably well for modern languages struggle with (the lack of) typographical conventions in 19th-century literature. While machine learning approaches to sequence modeling can be applied to solve the task, they typically face a severed skewness in the availability of training material, especially for lesser resourced languages. In this paper, we report the result of a multilingual approach to direct speech detection in a diverse corpus of 19th-century fiction in 9 European languages. The proposed method finetunes a transformer architecture with multilingual sentence embedder on a minimal amount of annotated training in each language, and improves performance across languages with ambiguous direct speech marking, in comparison to a carefully constructed regular expression baseline.
%U https://aclanthology.org/2020.lt4hala-1.15
%P 100-104
Markdown (Informal)
[Detecting Direct Speech in Multilingual Collection of 19th-century Novels](https://aclanthology.org/2020.lt4hala-1.15) (Byszuk et al., LT4HALA 2020)
ACL
- Joanna Byszuk, Michał Woźniak, Mike Kestemont, Albert Leśniak, Wojciech Łukasik, Artjoms Šeļa, and Maciej Eder. 2020. Detecting Direct Speech in Multilingual Collection of 19th-century Novels. In Proceedings of LT4HALA 2020 - 1st Workshop on Language Technologies for Historical and Ancient Languages, pages 100–104, Marseille, France. European Language Resources Association (ELRA).