@inproceedings{ali-etal-2024-monolingual,
title = "Monolingual Paraphrase Detection Corpus for Low Resource {P}ashto Language at Sentence Level",
author = "Ali, Iqra and
Kamigaito, Hidetaka and
Watanabe, Taro",
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.1011",
pages = "11574--11581",
abstract = "Paraphrase detection is a task to identify if two sentences are semantically similar or not. It plays an important role in maintaining the integrity of written work such as plagiarism detection and text reuse detection. Formerly, researchers focused on developing large corpora for English. However, no research has been conducted on sentence-level paraphrase detection in low-resource Pashto language. To bridge this gap, we introduce the first fully manually annotated Pashto sentential paraphrase detection corpus collected from authentic cases in journalism covering 10 different domains, including Sports, Health, Environment, and more. Our proposed corpus contains 6,727 sentences, encompassing 3,687 paraphrased and 3,040 non-paraphrased. Experimental findings reveal that our proposed corpus is sufficient to train XLM-RoBERTa to accurately detect paraphrased sentence pairs in Pashto with an F1 score of 84{\%}. To compare our corpus with those in other languages, we also applied our fine-tuned model to the Indonesian and English paraphrase datasets in a zero-shot manner, achieving F1 scores of 82{\%} and 78{\%}, respectively. This result indicates that the quality of our corpus is not less than commonly used datasets. It{`}s a pioneering contribution to the field. We will publicize a subset of 1,800 instances from our corpus, free from any licensing issues.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ali-etal-2024-monolingual">
<titleInfo>
<title>Monolingual Paraphrase Detection Corpus for Low Resource Pashto Language at Sentence Level</title>
</titleInfo>
<name type="personal">
<namePart type="given">Iqra</namePart>
<namePart type="family">Ali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hidetaka</namePart>
<namePart type="family">Kamigaito</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taro</namePart>
<namePart type="family">Watanabe</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>Paraphrase detection is a task to identify if two sentences are semantically similar or not. It plays an important role in maintaining the integrity of written work such as plagiarism detection and text reuse detection. Formerly, researchers focused on developing large corpora for English. However, no research has been conducted on sentence-level paraphrase detection in low-resource Pashto language. To bridge this gap, we introduce the first fully manually annotated Pashto sentential paraphrase detection corpus collected from authentic cases in journalism covering 10 different domains, including Sports, Health, Environment, and more. Our proposed corpus contains 6,727 sentences, encompassing 3,687 paraphrased and 3,040 non-paraphrased. Experimental findings reveal that our proposed corpus is sufficient to train XLM-RoBERTa to accurately detect paraphrased sentence pairs in Pashto with an F1 score of 84%. To compare our corpus with those in other languages, we also applied our fine-tuned model to the Indonesian and English paraphrase datasets in a zero-shot manner, achieving F1 scores of 82% and 78%, respectively. This result indicates that the quality of our corpus is not less than commonly used datasets. It‘s a pioneering contribution to the field. We will publicize a subset of 1,800 instances from our corpus, free from any licensing issues.</abstract>
<identifier type="citekey">ali-etal-2024-monolingual</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1011</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>11574</start>
<end>11581</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Monolingual Paraphrase Detection Corpus for Low Resource Pashto Language at Sentence Level
%A Ali, Iqra
%A Kamigaito, Hidetaka
%A Watanabe, Taro
%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 ali-etal-2024-monolingual
%X Paraphrase detection is a task to identify if two sentences are semantically similar or not. It plays an important role in maintaining the integrity of written work such as plagiarism detection and text reuse detection. Formerly, researchers focused on developing large corpora for English. However, no research has been conducted on sentence-level paraphrase detection in low-resource Pashto language. To bridge this gap, we introduce the first fully manually annotated Pashto sentential paraphrase detection corpus collected from authentic cases in journalism covering 10 different domains, including Sports, Health, Environment, and more. Our proposed corpus contains 6,727 sentences, encompassing 3,687 paraphrased and 3,040 non-paraphrased. Experimental findings reveal that our proposed corpus is sufficient to train XLM-RoBERTa to accurately detect paraphrased sentence pairs in Pashto with an F1 score of 84%. To compare our corpus with those in other languages, we also applied our fine-tuned model to the Indonesian and English paraphrase datasets in a zero-shot manner, achieving F1 scores of 82% and 78%, respectively. This result indicates that the quality of our corpus is not less than commonly used datasets. It‘s a pioneering contribution to the field. We will publicize a subset of 1,800 instances from our corpus, free from any licensing issues.
%U https://aclanthology.org/2024.lrec-main.1011
%P 11574-11581
Markdown (Informal)
[Monolingual Paraphrase Detection Corpus for Low Resource Pashto Language at Sentence Level](https://aclanthology.org/2024.lrec-main.1011) (Ali et al., LREC-COLING 2024)
ACL