@inproceedings{ponce-etal-2023-unsupervised,
title = "Unsupervised Subtitle Segmentation with Masked Language Models",
author = "Ponce, David and
Etchegoyhen, Thierry and
Ruiz, Victor",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-short.67",
doi = "10.18653/v1/2023.acl-short.67",
pages = "771--781",
abstract = "We describe a novel unsupervised approach to subtitle segmentation, based on pretrained masked language models, where line endings and subtitle breaks are predicted according to the likelihood of punctuation to occur at candidate segmentation points. Our approach obtained competitive results in terms of segmentation accuracy across metrics, while also fully preserving the original text and complying with length constraints. Although supervised models trained on in-domain data and with access to source audio information can provide better segmentation accuracy, our approach is highly portable across languages and domains and may constitute a robust off-the-shelf solution for subtitle segmentation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ponce-etal-2023-unsupervised">
<titleInfo>
<title>Unsupervised Subtitle Segmentation with Masked Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Ponce</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Etchegoyhen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Victor</namePart>
<namePart type="family">Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We describe a novel unsupervised approach to subtitle segmentation, based on pretrained masked language models, where line endings and subtitle breaks are predicted according to the likelihood of punctuation to occur at candidate segmentation points. Our approach obtained competitive results in terms of segmentation accuracy across metrics, while also fully preserving the original text and complying with length constraints. Although supervised models trained on in-domain data and with access to source audio information can provide better segmentation accuracy, our approach is highly portable across languages and domains and may constitute a robust off-the-shelf solution for subtitle segmentation.</abstract>
<identifier type="citekey">ponce-etal-2023-unsupervised</identifier>
<identifier type="doi">10.18653/v1/2023.acl-short.67</identifier>
<location>
<url>https://aclanthology.org/2023.acl-short.67</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>771</start>
<end>781</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unsupervised Subtitle Segmentation with Masked Language Models
%A Ponce, David
%A Etchegoyhen, Thierry
%A Ruiz, Victor
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F ponce-etal-2023-unsupervised
%X We describe a novel unsupervised approach to subtitle segmentation, based on pretrained masked language models, where line endings and subtitle breaks are predicted according to the likelihood of punctuation to occur at candidate segmentation points. Our approach obtained competitive results in terms of segmentation accuracy across metrics, while also fully preserving the original text and complying with length constraints. Although supervised models trained on in-domain data and with access to source audio information can provide better segmentation accuracy, our approach is highly portable across languages and domains and may constitute a robust off-the-shelf solution for subtitle segmentation.
%R 10.18653/v1/2023.acl-short.67
%U https://aclanthology.org/2023.acl-short.67
%U https://doi.org/10.18653/v1/2023.acl-short.67
%P 771-781
Markdown (Informal)
[Unsupervised Subtitle Segmentation with Masked Language Models](https://aclanthology.org/2023.acl-short.67) (Ponce et al., ACL 2023)
ACL
- David Ponce, Thierry Etchegoyhen, and Victor Ruiz. 2023. Unsupervised Subtitle Segmentation with Masked Language Models. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 771–781, Toronto, Canada. Association for Computational Linguistics.