@inproceedings{alfear-etal-2024-meta-evaluation,
title = "Meta-Evaluation of Sentence Simplification Metrics",
author = "Alfear, Noof Abdullah and
Kazakov, Dimitar and
Al-Khalifa, Hend",
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.981",
pages = "11229--11235",
abstract = "Automatic Text Simplification (ATS) is one of the major Natural Language Processing (NLP) tasks, which aims to help people understand text that is above their reading abilities and comprehension. ATS models reconstruct the text into a simpler format by deletion, substitution, addition or splitting, while preserving the original meaning and maintaining correct grammar. Simplified sentences are usually evaluated by human experts based on three main factors: simplicity, adequacy and fluency or by calculating automatic evaluation metrics. In this paper, we conduct a meta-evaluation of reference-based automatic metrics for English sentence simplification using high-quality, human-annotated dataset, NEWSELA-LIKERT. We study the behavior of several evaluation metrics at sentence level across four different sentence simplification models. All the models were trained on the NEWSELA-AUTO dataset. The correlation between the metrics{'} scores and human judgements was analyzed and the results used to recommend the most appropriate metrics for this task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alfear-etal-2024-meta-evaluation">
<titleInfo>
<title>Meta-Evaluation of Sentence Simplification Metrics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Noof</namePart>
<namePart type="given">Abdullah</namePart>
<namePart type="family">Alfear</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dimitar</namePart>
<namePart type="family">Kazakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</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>Automatic Text Simplification (ATS) is one of the major Natural Language Processing (NLP) tasks, which aims to help people understand text that is above their reading abilities and comprehension. ATS models reconstruct the text into a simpler format by deletion, substitution, addition or splitting, while preserving the original meaning and maintaining correct grammar. Simplified sentences are usually evaluated by human experts based on three main factors: simplicity, adequacy and fluency or by calculating automatic evaluation metrics. In this paper, we conduct a meta-evaluation of reference-based automatic metrics for English sentence simplification using high-quality, human-annotated dataset, NEWSELA-LIKERT. We study the behavior of several evaluation metrics at sentence level across four different sentence simplification models. All the models were trained on the NEWSELA-AUTO dataset. The correlation between the metrics’ scores and human judgements was analyzed and the results used to recommend the most appropriate metrics for this task.</abstract>
<identifier type="citekey">alfear-etal-2024-meta-evaluation</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.981</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>11229</start>
<end>11235</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Meta-Evaluation of Sentence Simplification Metrics
%A Alfear, Noof Abdullah
%A Kazakov, Dimitar
%A Al-Khalifa, Hend
%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 alfear-etal-2024-meta-evaluation
%X Automatic Text Simplification (ATS) is one of the major Natural Language Processing (NLP) tasks, which aims to help people understand text that is above their reading abilities and comprehension. ATS models reconstruct the text into a simpler format by deletion, substitution, addition or splitting, while preserving the original meaning and maintaining correct grammar. Simplified sentences are usually evaluated by human experts based on three main factors: simplicity, adequacy and fluency or by calculating automatic evaluation metrics. In this paper, we conduct a meta-evaluation of reference-based automatic metrics for English sentence simplification using high-quality, human-annotated dataset, NEWSELA-LIKERT. We study the behavior of several evaluation metrics at sentence level across four different sentence simplification models. All the models were trained on the NEWSELA-AUTO dataset. The correlation between the metrics’ scores and human judgements was analyzed and the results used to recommend the most appropriate metrics for this task.
%U https://aclanthology.org/2024.lrec-main.981
%P 11229-11235
Markdown (Informal)
[Meta-Evaluation of Sentence Simplification Metrics](https://aclanthology.org/2024.lrec-main.981) (Alfear et al., LREC-COLING 2024)
ACL
- Noof Abdullah Alfear, Dimitar Kazakov, and Hend Al-Khalifa. 2024. Meta-Evaluation of Sentence Simplification Metrics. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 11229–11235, Torino, Italia. ELRA and ICCL.