@inproceedings{heyns-van-zaanen-2022-detecting,
title = "Detecting Multiple Transitions in Literary Texts",
author = "Heyns, Nuette and
van Zaanen, Menno",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.360",
pages = "3375--3381",
abstract = "Identifying the high level structure of texts provides important information when performing distant reading analysis. The structure of texts is not necessarily linear, as transitions, such as changes in the scenery or flashbacks, can be present. As a first step in identifying this structure, we aim to identify transitions in texts. Previous work (Heyns and van Zaanen, 2021) proposed a system that can successfully identify one transition in literary texts. The text is split in snippets and LDA is applied, resulting in a sequence of topics. A transition is introduced at the point that separates the topics (before and after the point) best. In this article, we extend the existing system such that it can detect multiple transitions. Additionally, we introduce a new system that inherently handles multiple transitions in texts. The new system also relies on LDA information, but is more robust than the previous system. We apply these systems to texts with known transitions (as they are constructed by concatenating text snippets stemming from different source texts) and evaluation both systems on texts with one transition and texts with two transitions. As both systems rely on LDA to identify transitions between snippets, we also show the impact of varying the number of LDA topics on the results as well. The new system consistently outperforms the previous system, not only on texts with multiple transitions, but also on single boundary texts.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="heyns-van-zaanen-2022-detecting">
<titleInfo>
<title>Detecting Multiple Transitions in Literary Texts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nuette</namePart>
<namePart type="family">Heyns</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Menno</namePart>
<namePart type="family">van Zaanen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Identifying the high level structure of texts provides important information when performing distant reading analysis. The structure of texts is not necessarily linear, as transitions, such as changes in the scenery or flashbacks, can be present. As a first step in identifying this structure, we aim to identify transitions in texts. Previous work (Heyns and van Zaanen, 2021) proposed a system that can successfully identify one transition in literary texts. The text is split in snippets and LDA is applied, resulting in a sequence of topics. A transition is introduced at the point that separates the topics (before and after the point) best. In this article, we extend the existing system such that it can detect multiple transitions. Additionally, we introduce a new system that inherently handles multiple transitions in texts. The new system also relies on LDA information, but is more robust than the previous system. We apply these systems to texts with known transitions (as they are constructed by concatenating text snippets stemming from different source texts) and evaluation both systems on texts with one transition and texts with two transitions. As both systems rely on LDA to identify transitions between snippets, we also show the impact of varying the number of LDA topics on the results as well. The new system consistently outperforms the previous system, not only on texts with multiple transitions, but also on single boundary texts.</abstract>
<identifier type="citekey">heyns-van-zaanen-2022-detecting</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.360</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>3375</start>
<end>3381</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Detecting Multiple Transitions in Literary Texts
%A Heyns, Nuette
%A van Zaanen, Menno
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F heyns-van-zaanen-2022-detecting
%X Identifying the high level structure of texts provides important information when performing distant reading analysis. The structure of texts is not necessarily linear, as transitions, such as changes in the scenery or flashbacks, can be present. As a first step in identifying this structure, we aim to identify transitions in texts. Previous work (Heyns and van Zaanen, 2021) proposed a system that can successfully identify one transition in literary texts. The text is split in snippets and LDA is applied, resulting in a sequence of topics. A transition is introduced at the point that separates the topics (before and after the point) best. In this article, we extend the existing system such that it can detect multiple transitions. Additionally, we introduce a new system that inherently handles multiple transitions in texts. The new system also relies on LDA information, but is more robust than the previous system. We apply these systems to texts with known transitions (as they are constructed by concatenating text snippets stemming from different source texts) and evaluation both systems on texts with one transition and texts with two transitions. As both systems rely on LDA to identify transitions between snippets, we also show the impact of varying the number of LDA topics on the results as well. The new system consistently outperforms the previous system, not only on texts with multiple transitions, but also on single boundary texts.
%U https://aclanthology.org/2022.lrec-1.360
%P 3375-3381
Markdown (Informal)
[Detecting Multiple Transitions in Literary Texts](https://aclanthology.org/2022.lrec-1.360) (Heyns & van Zaanen, LREC 2022)
ACL
- Nuette Heyns and Menno van Zaanen. 2022. Detecting Multiple Transitions in Literary Texts. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 3375–3381, Marseille, France. European Language Resources Association.