@inproceedings{retkowski-waibel-2024-text,
title = "From Text Segmentation to Smart Chaptering: A Novel Benchmark for Structuring Video Transcriptions",
author = "Retkowski, Fabian and
Waibel, Alexander",
editor = "Graham, Yvette and
Purver, Matthew",
booktitle = "Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = mar,
year = "2024",
address = "St. Julian{'}s, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.eacl-long.25",
pages = "406--419",
abstract = "Text segmentation is a fundamental task in natural language processing, where documents are split into contiguous sections. However, prior research in this area has been constrained by limited datasets, which are either small in scale, synthesized, or only contain well-structured documents. In this paper, we address these limitations by introducing a novel benchmark YTSeg focusing on spoken content that is inherently more unstructured and both topically and structurally diverse. As part of this work, we introduce an efficient hierarchical segmentation model MiniSeg, that outperforms state-of-the-art baselines. Lastly, we expand the notion of text segmentation to a more practical {``}smart chaptering{''} task that involves the segmentation of unstructured content, the generation of meaningful segment titles, and a potential real-time application of the models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="retkowski-waibel-2024-text">
<titleInfo>
<title>From Text Segmentation to Smart Chaptering: A Novel Benchmark for Structuring Video Transcriptions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fabian</namePart>
<namePart type="family">Retkowski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Waibel</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 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Purver</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julian’s, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Text segmentation is a fundamental task in natural language processing, where documents are split into contiguous sections. However, prior research in this area has been constrained by limited datasets, which are either small in scale, synthesized, or only contain well-structured documents. In this paper, we address these limitations by introducing a novel benchmark YTSeg focusing on spoken content that is inherently more unstructured and both topically and structurally diverse. As part of this work, we introduce an efficient hierarchical segmentation model MiniSeg, that outperforms state-of-the-art baselines. Lastly, we expand the notion of text segmentation to a more practical “smart chaptering” task that involves the segmentation of unstructured content, the generation of meaningful segment titles, and a potential real-time application of the models.</abstract>
<identifier type="citekey">retkowski-waibel-2024-text</identifier>
<location>
<url>https://aclanthology.org/2024.eacl-long.25</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>406</start>
<end>419</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From Text Segmentation to Smart Chaptering: A Novel Benchmark for Structuring Video Transcriptions
%A Retkowski, Fabian
%A Waibel, Alexander
%Y Graham, Yvette
%Y Purver, Matthew
%S Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F retkowski-waibel-2024-text
%X Text segmentation is a fundamental task in natural language processing, where documents are split into contiguous sections. However, prior research in this area has been constrained by limited datasets, which are either small in scale, synthesized, or only contain well-structured documents. In this paper, we address these limitations by introducing a novel benchmark YTSeg focusing on spoken content that is inherently more unstructured and both topically and structurally diverse. As part of this work, we introduce an efficient hierarchical segmentation model MiniSeg, that outperforms state-of-the-art baselines. Lastly, we expand the notion of text segmentation to a more practical “smart chaptering” task that involves the segmentation of unstructured content, the generation of meaningful segment titles, and a potential real-time application of the models.
%U https://aclanthology.org/2024.eacl-long.25
%P 406-419
Markdown (Informal)
[From Text Segmentation to Smart Chaptering: A Novel Benchmark for Structuring Video Transcriptions](https://aclanthology.org/2024.eacl-long.25) (Retkowski & Waibel, EACL 2024)
ACL