@inproceedings{abbasi-etal-2025-neural,
title = "Neural Document Segmentation Using Weighted Sliding Windows with Transformer Encoders",
author = "Abbasi, Saeed and
An, Aijun and
Davoudi, Heidar and
Di Carlantonio, Ron and
Farmaner, Gary",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven and
Darwish, Kareem and
Agarwal, Apoorv",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics: Industry Track",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-industry.67/",
pages = "807--816",
abstract = "We introduce a novel Transformer-based method for document segmentation, tailored for practical, real-world applications. This method utilizes overlapping text sequences with a unique position-aware weighting mechanism to enhance segmentation accuracy. Through comprehensive experiments on both public and proprietary datasets, we demonstrate significant improvements, establishing new state-of-the-art standards by achieving up to a 10{\%} increase in segmentation F1 score compared to existing methods. Additionally, we explore the application of our segmentation method in downstream retrieval-augmented question answering tasks, where it improves the quality of generated responses by 5{\%} while achieving up to four times greater efficiency. These results underscore our model`s potential as a robust and scalable solution for real-world text segmentation challenges."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="abbasi-etal-2025-neural">
<titleInfo>
<title>Neural Document Segmentation Using Weighted Sliding Windows with Transformer Encoders</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saeed</namePart>
<namePart type="family">Abbasi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aijun</namePart>
<namePart type="family">An</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heidar</namePart>
<namePart type="family">Davoudi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ron</namePart>
<namePart type="family">Di Carlantonio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gary</namePart>
<namePart type="family">Farmaner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Apoorv</namePart>
<namePart type="family">Agarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce a novel Transformer-based method for document segmentation, tailored for practical, real-world applications. This method utilizes overlapping text sequences with a unique position-aware weighting mechanism to enhance segmentation accuracy. Through comprehensive experiments on both public and proprietary datasets, we demonstrate significant improvements, establishing new state-of-the-art standards by achieving up to a 10% increase in segmentation F1 score compared to existing methods. Additionally, we explore the application of our segmentation method in downstream retrieval-augmented question answering tasks, where it improves the quality of generated responses by 5% while achieving up to four times greater efficiency. These results underscore our model‘s potential as a robust and scalable solution for real-world text segmentation challenges.</abstract>
<identifier type="citekey">abbasi-etal-2025-neural</identifier>
<location>
<url>https://aclanthology.org/2025.coling-industry.67/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>807</start>
<end>816</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Neural Document Segmentation Using Weighted Sliding Windows with Transformer Encoders
%A Abbasi, Saeed
%A An, Aijun
%A Davoudi, Heidar
%A Di Carlantonio, Ron
%A Farmaner, Gary
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%Y Darwish, Kareem
%Y Agarwal, Apoorv
%S Proceedings of the 31st International Conference on Computational Linguistics: Industry Track
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F abbasi-etal-2025-neural
%X We introduce a novel Transformer-based method for document segmentation, tailored for practical, real-world applications. This method utilizes overlapping text sequences with a unique position-aware weighting mechanism to enhance segmentation accuracy. Through comprehensive experiments on both public and proprietary datasets, we demonstrate significant improvements, establishing new state-of-the-art standards by achieving up to a 10% increase in segmentation F1 score compared to existing methods. Additionally, we explore the application of our segmentation method in downstream retrieval-augmented question answering tasks, where it improves the quality of generated responses by 5% while achieving up to four times greater efficiency. These results underscore our model‘s potential as a robust and scalable solution for real-world text segmentation challenges.
%U https://aclanthology.org/2025.coling-industry.67/
%P 807-816
Markdown (Informal)
[Neural Document Segmentation Using Weighted Sliding Windows with Transformer Encoders](https://aclanthology.org/2025.coling-industry.67/) (Abbasi et al., COLING 2025)
ACL