@inproceedings{calleja-etal-2024-automating,
title = "Automating Easy Read Text Segmentation",
author = "Calleja, Jesus and
Etchegoyhen, Thierry and
Ponce Mart{\'\i}nez, Antonio David",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.694",
pages = "11876--11894",
abstract = "Easy Read text is one of the main forms of access to information for people with reading difficulties. One of the key characteristics of this type of text is the requirement to split sentences into smaller grammatical segments, to facilitate reading. Automated segmentation methods could foster the creation of Easy Read content, but their viability has yet to be addressed. In this work, we study novel methods for the task, leveraging masked and generative language models, along with constituent parsing. We conduct comprehensive automatic and human evaluations in three languages, analysing the strengths and weaknesses of the proposed alternatives, under scarce resource limitations. Our results highlight the viability of automated Easy Read segmentation and remaining deficiencies compared to expert-driven human segmentation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="calleja-etal-2024-automating">
<titleInfo>
<title>Automating Easy Read Text Segmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jesus</namePart>
<namePart type="family">Calleja</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">Antonio</namePart>
<namePart type="given">David</namePart>
<namePart type="family">Ponce Martínez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Easy Read text is one of the main forms of access to information for people with reading difficulties. One of the key characteristics of this type of text is the requirement to split sentences into smaller grammatical segments, to facilitate reading. Automated segmentation methods could foster the creation of Easy Read content, but their viability has yet to be addressed. In this work, we study novel methods for the task, leveraging masked and generative language models, along with constituent parsing. We conduct comprehensive automatic and human evaluations in three languages, analysing the strengths and weaknesses of the proposed alternatives, under scarce resource limitations. Our results highlight the viability of automated Easy Read segmentation and remaining deficiencies compared to expert-driven human segmentation.</abstract>
<identifier type="citekey">calleja-etal-2024-automating</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.694</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>11876</start>
<end>11894</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automating Easy Read Text Segmentation
%A Calleja, Jesus
%A Etchegoyhen, Thierry
%A Ponce Martínez, Antonio David
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F calleja-etal-2024-automating
%X Easy Read text is one of the main forms of access to information for people with reading difficulties. One of the key characteristics of this type of text is the requirement to split sentences into smaller grammatical segments, to facilitate reading. Automated segmentation methods could foster the creation of Easy Read content, but their viability has yet to be addressed. In this work, we study novel methods for the task, leveraging masked and generative language models, along with constituent parsing. We conduct comprehensive automatic and human evaluations in three languages, analysing the strengths and weaknesses of the proposed alternatives, under scarce resource limitations. Our results highlight the viability of automated Easy Read segmentation and remaining deficiencies compared to expert-driven human segmentation.
%U https://aclanthology.org/2024.findings-emnlp.694
%P 11876-11894
Markdown (Informal)
[Automating Easy Read Text Segmentation](https://aclanthology.org/2024.findings-emnlp.694) (Calleja et al., Findings 2024)
ACL
- Jesus Calleja, Thierry Etchegoyhen, and Antonio David Ponce Martínez. 2024. Automating Easy Read Text Segmentation. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 11876–11894, Miami, Florida, USA. Association for Computational Linguistics.