@inproceedings{stymne-2024-direct,
title = "Direct Speech Identification in {S}wedish Literature and an Exploration of Training Data Type, Typographical Markers, and Evaluation Granularity",
author = "Stymne, Sara",
editor = "Bizzoni, Yuri and
Degaetano-Ortlieb, Stefania and
Kazantseva, Anna and
Szpakowicz, Stan",
booktitle = "Proceedings of the 8th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (LaTeCH-CLfL 2024)",
month = mar,
year = "2024",
address = "St. Julians, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.latechclfl-1.25",
pages = "253--263",
abstract = "Identifying direct speech in literary fiction is challenging for cases that do not mark speech segments with quotation marks. Such efforts have previously been based either on smaller manually annotated gold data or larger automatically annotated silver data, extracted from works with quotation marks. However, no direct comparison has so far been made between the performance of these two types of training data. In this work, we address this gap. We further explore the effect of different types of typographical speech marking and of using evaluation metrics of different granularity. We perform experiments on Swedish literary texts and find that using gold and silver data has different strengths, with gold data having stronger results on token-level metrics, whereas silver data overall has stronger results on span-level metrics. If the training data contains some data that matches the typographical speech marking of the target, that is generally sufficient for achieving good results, but it does not seem to hurt if the training data also contains other types of marking.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="stymne-2024-direct">
<titleInfo>
<title>Direct Speech Identification in Swedish Literature and an Exploration of Training Data Type, Typographical Markers, and Evaluation Granularity</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Stymne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 8th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (LaTeCH-CLfL 2024)</title>
</titleInfo>
<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">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">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">St. Julians, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Identifying direct speech in literary fiction is challenging for cases that do not mark speech segments with quotation marks. Such efforts have previously been based either on smaller manually annotated gold data or larger automatically annotated silver data, extracted from works with quotation marks. However, no direct comparison has so far been made between the performance of these two types of training data. In this work, we address this gap. We further explore the effect of different types of typographical speech marking and of using evaluation metrics of different granularity. We perform experiments on Swedish literary texts and find that using gold and silver data has different strengths, with gold data having stronger results on token-level metrics, whereas silver data overall has stronger results on span-level metrics. If the training data contains some data that matches the typographical speech marking of the target, that is generally sufficient for achieving good results, but it does not seem to hurt if the training data also contains other types of marking.</abstract>
<identifier type="citekey">stymne-2024-direct</identifier>
<location>
<url>https://aclanthology.org/2024.latechclfl-1.25</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>253</start>
<end>263</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Direct Speech Identification in Swedish Literature and an Exploration of Training Data Type, Typographical Markers, and Evaluation Granularity
%A Stymne, Sara
%Y Bizzoni, Yuri
%Y Degaetano-Ortlieb, Stefania
%Y Kazantseva, Anna
%Y Szpakowicz, Stan
%S Proceedings of the 8th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (LaTeCH-CLfL 2024)
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julians, Malta
%F stymne-2024-direct
%X Identifying direct speech in literary fiction is challenging for cases that do not mark speech segments with quotation marks. Such efforts have previously been based either on smaller manually annotated gold data or larger automatically annotated silver data, extracted from works with quotation marks. However, no direct comparison has so far been made between the performance of these two types of training data. In this work, we address this gap. We further explore the effect of different types of typographical speech marking and of using evaluation metrics of different granularity. We perform experiments on Swedish literary texts and find that using gold and silver data has different strengths, with gold data having stronger results on token-level metrics, whereas silver data overall has stronger results on span-level metrics. If the training data contains some data that matches the typographical speech marking of the target, that is generally sufficient for achieving good results, but it does not seem to hurt if the training data also contains other types of marking.
%U https://aclanthology.org/2024.latechclfl-1.25
%P 253-263
Markdown (Informal)
[Direct Speech Identification in Swedish Literature and an Exploration of Training Data Type, Typographical Markers, and Evaluation Granularity](https://aclanthology.org/2024.latechclfl-1.25) (Stymne, LaTeCHCLfL-WS 2024)
ACL