@inproceedings{sun-etal-2023-exploiting,
title = "Exploiting Summarization Data to Help Text Simplification",
author = "Sun, Renliang and
Yang, Zhixian and
Wan, Xiaojun",
editor = "Vlachos, Andreas and
Augenstein, Isabelle",
booktitle = "Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.eacl-main.3",
doi = "10.18653/v1/2023.eacl-main.3",
pages = "39--51",
abstract = "One of the major problems with text simplification is the lack of high-quality data. The sources of simplification datasets are limited to Wikipedia and Newsela, restricting further development of this field. In this paper, we analyzed the similarity between text summarization and text simplification and exploited summarization data to help simplify. First, we proposed an alignment algorithm to extract sentence pairs from summarization datasets. Then, we designed four attributes to characterize the degree of simplification and proposed a method to filter suitable pairs. We named these pairs Sum4Simp (S4S). Next, we conducted human evaluations to show that S4S is high-quality and compared it with a real simplification dataset. Finally, we conducted experiments to illustrate that the S4S can improve the performance of several mainstream simplification models, especially in low-resource scenarios.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sun-etal-2023-exploiting">
<titleInfo>
<title>Exploiting Summarization Data to Help Text Simplification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Renliang</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhixian</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>One of the major problems with text simplification is the lack of high-quality data. The sources of simplification datasets are limited to Wikipedia and Newsela, restricting further development of this field. In this paper, we analyzed the similarity between text summarization and text simplification and exploited summarization data to help simplify. First, we proposed an alignment algorithm to extract sentence pairs from summarization datasets. Then, we designed four attributes to characterize the degree of simplification and proposed a method to filter suitable pairs. We named these pairs Sum4Simp (S4S). Next, we conducted human evaluations to show that S4S is high-quality and compared it with a real simplification dataset. Finally, we conducted experiments to illustrate that the S4S can improve the performance of several mainstream simplification models, especially in low-resource scenarios.</abstract>
<identifier type="citekey">sun-etal-2023-exploiting</identifier>
<identifier type="doi">10.18653/v1/2023.eacl-main.3</identifier>
<location>
<url>https://aclanthology.org/2023.eacl-main.3</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>39</start>
<end>51</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploiting Summarization Data to Help Text Simplification
%A Sun, Renliang
%A Yang, Zhixian
%A Wan, Xiaojun
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F sun-etal-2023-exploiting
%X One of the major problems with text simplification is the lack of high-quality data. The sources of simplification datasets are limited to Wikipedia and Newsela, restricting further development of this field. In this paper, we analyzed the similarity between text summarization and text simplification and exploited summarization data to help simplify. First, we proposed an alignment algorithm to extract sentence pairs from summarization datasets. Then, we designed four attributes to characterize the degree of simplification and proposed a method to filter suitable pairs. We named these pairs Sum4Simp (S4S). Next, we conducted human evaluations to show that S4S is high-quality and compared it with a real simplification dataset. Finally, we conducted experiments to illustrate that the S4S can improve the performance of several mainstream simplification models, especially in low-resource scenarios.
%R 10.18653/v1/2023.eacl-main.3
%U https://aclanthology.org/2023.eacl-main.3
%U https://doi.org/10.18653/v1/2023.eacl-main.3
%P 39-51
Markdown (Informal)
[Exploiting Summarization Data to Help Text Simplification](https://aclanthology.org/2023.eacl-main.3) (Sun et al., EACL 2023)
ACL
- Renliang Sun, Zhixian Yang, and Xiaojun Wan. 2023. Exploiting Summarization Data to Help Text Simplification. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 39–51, Dubrovnik, Croatia. Association for Computational Linguistics.