@inproceedings{liu-lee-2024-csswiki,
title = "{CSSW}iki: A {C}hinese Sentence Simplification Dataset with Linguistic and Content Operations",
author = "Liu, Fengkai and
Lee, John S. Y.",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.375/",
pages = "4205--4213",
abstract = "Sentence Simplification aims to make sentences easier to read and understand. With most effort on corpus development focused on English, the amount of annotated data is limited in Chinese. To address this need, we introduce CSSWiki, an open-source dataset for Chinese sentence simplification based on Wikipedia. This dataset contains 1.6k source sentences paired with their simplified versions. Each sentence pair is annotated with operation tags that distinguish between linguistic and content modifications. We analyze differences in annotation scheme and data statistics between CSSWiki and existing datasets. We then report baseline sentence simplification performance on CSSWiki using zero-shot and few-shot approaches with Large Language Models."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-lee-2024-csswiki">
<titleInfo>
<title>CSSWiki: A Chinese Sentence Simplification Dataset with Linguistic and Content Operations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fengkai</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="given">S</namePart>
<namePart type="given">Y</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Sentence Simplification aims to make sentences easier to read and understand. With most effort on corpus development focused on English, the amount of annotated data is limited in Chinese. To address this need, we introduce CSSWiki, an open-source dataset for Chinese sentence simplification based on Wikipedia. This dataset contains 1.6k source sentences paired with their simplified versions. Each sentence pair is annotated with operation tags that distinguish between linguistic and content modifications. We analyze differences in annotation scheme and data statistics between CSSWiki and existing datasets. We then report baseline sentence simplification performance on CSSWiki using zero-shot and few-shot approaches with Large Language Models.</abstract>
<identifier type="citekey">liu-lee-2024-csswiki</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.375/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>4205</start>
<end>4213</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CSSWiki: A Chinese Sentence Simplification Dataset with Linguistic and Content Operations
%A Liu, Fengkai
%A Lee, John S. Y.
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F liu-lee-2024-csswiki
%X Sentence Simplification aims to make sentences easier to read and understand. With most effort on corpus development focused on English, the amount of annotated data is limited in Chinese. To address this need, we introduce CSSWiki, an open-source dataset for Chinese sentence simplification based on Wikipedia. This dataset contains 1.6k source sentences paired with their simplified versions. Each sentence pair is annotated with operation tags that distinguish between linguistic and content modifications. We analyze differences in annotation scheme and data statistics between CSSWiki and existing datasets. We then report baseline sentence simplification performance on CSSWiki using zero-shot and few-shot approaches with Large Language Models.
%U https://aclanthology.org/2024.lrec-main.375/
%P 4205-4213
Markdown (Informal)
[CSSWiki: A Chinese Sentence Simplification Dataset with Linguistic and Content Operations](https://aclanthology.org/2024.lrec-main.375/) (Liu & Lee, LREC-COLING 2024)
ACL