@inproceedings{nomoto-2022-fewer,
title = "The Fewer Splits are Better: Deconstructing Readability in Sentence Splitting",
author = "Nomoto, Tadashi",
editor = "{\v{S}}tajner, Sanja and
Saggion, Horacio and
Ferr{\'e}s, Daniel and
Shardlow, Matthew and
Sheang, Kim Cheng and
North, Kai and
Zampieri, Marcos and
Xu, Wei",
booktitle = "Proceedings of the Workshop on Text Simplification, Accessibility, and Readability (TSAR-2022)",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Virtual)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.tsar-1.1",
doi = "10.18653/v1/2022.tsar-1.1",
pages = "1--11",
abstract = "In this work, we focus on sentence splitting, a subfield of text simplification, primarily motivated by an unproven idea that if you divide a sentence into pieces, it should become easier to understand. Our primary goal in this paper is to determine whether this is true. In particular, we ask, does it matter whether we break a sentence into two or three? We report on our findings based on Amazon Mechanical Turk. More specifically, we introduce a Bayesian modeling framework to further investigate to what degree a particular way of splitting the complex sentence affects readability, along with a number of other parameters adopted from diverse perspectives, including clinical linguistics, and cognitive linguistics. The Bayesian modeling experiment provides clear evidence that bisecting the sentence leads to enhanced readability to a degree greater than when we create simplification by trisection.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nomoto-2022-fewer">
<titleInfo>
<title>The Fewer Splits are Better: Deconstructing Readability in Sentence Splitting</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tadashi</namePart>
<namePart type="family">Nomoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Text Simplification, Accessibility, and Readability (TSAR-2022)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sanja</namePart>
<namePart type="family">Štajner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Horacio</namePart>
<namePart type="family">Saggion</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Ferrés</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Shardlow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kim</namePart>
<namePart type="given">Cheng</namePart>
<namePart type="family">Sheang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">North</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates (Virtual)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this work, we focus on sentence splitting, a subfield of text simplification, primarily motivated by an unproven idea that if you divide a sentence into pieces, it should become easier to understand. Our primary goal in this paper is to determine whether this is true. In particular, we ask, does it matter whether we break a sentence into two or three? We report on our findings based on Amazon Mechanical Turk. More specifically, we introduce a Bayesian modeling framework to further investigate to what degree a particular way of splitting the complex sentence affects readability, along with a number of other parameters adopted from diverse perspectives, including clinical linguistics, and cognitive linguistics. The Bayesian modeling experiment provides clear evidence that bisecting the sentence leads to enhanced readability to a degree greater than when we create simplification by trisection.</abstract>
<identifier type="citekey">nomoto-2022-fewer</identifier>
<identifier type="doi">10.18653/v1/2022.tsar-1.1</identifier>
<location>
<url>https://aclanthology.org/2022.tsar-1.1</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>1</start>
<end>11</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Fewer Splits are Better: Deconstructing Readability in Sentence Splitting
%A Nomoto, Tadashi
%Y Štajner, Sanja
%Y Saggion, Horacio
%Y Ferrés, Daniel
%Y Shardlow, Matthew
%Y Sheang, Kim Cheng
%Y North, Kai
%Y Zampieri, Marcos
%Y Xu, Wei
%S Proceedings of the Workshop on Text Simplification, Accessibility, and Readability (TSAR-2022)
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Virtual)
%F nomoto-2022-fewer
%X In this work, we focus on sentence splitting, a subfield of text simplification, primarily motivated by an unproven idea that if you divide a sentence into pieces, it should become easier to understand. Our primary goal in this paper is to determine whether this is true. In particular, we ask, does it matter whether we break a sentence into two or three? We report on our findings based on Amazon Mechanical Turk. More specifically, we introduce a Bayesian modeling framework to further investigate to what degree a particular way of splitting the complex sentence affects readability, along with a number of other parameters adopted from diverse perspectives, including clinical linguistics, and cognitive linguistics. The Bayesian modeling experiment provides clear evidence that bisecting the sentence leads to enhanced readability to a degree greater than when we create simplification by trisection.
%R 10.18653/v1/2022.tsar-1.1
%U https://aclanthology.org/2022.tsar-1.1
%U https://doi.org/10.18653/v1/2022.tsar-1.1
%P 1-11
Markdown (Informal)
[The Fewer Splits are Better: Deconstructing Readability in Sentence Splitting](https://aclanthology.org/2022.tsar-1.1) (Nomoto, TSAR 2022)
ACL