@inproceedings{jafari-harandi-etal-2024-epoque-english,
title = "{EPOQUE}: An {E}nglish-{P}ersian Quality Estimation Dataset",
author = "Jafari Harandi, Mohammed Hossein and
Azadi, Fatemeh and
Dousti, Mohammad Javad and
Faili, Heshaam",
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.550",
pages = "6228--6235",
abstract = "Translation quality estimation (QE) is an important component in real-world machine translation applications. Unfortunately, human labeled QE datasets, which play an important role in developing and assessing QE models, are only available for limited language pairs. In this paper, we present the first English-Persian QE dataset, called EPOQUE, which has manually annotated direct assessment labels. EPOQUE contains 1000 sentences translated from English to Persian and annotated by three human annotators. It is publicly available, and thus can be used as a zero-shot test set, or for other scenarios in future work. We also evaluate and report the performance of two state-of-the-art QE models, i.e., Transquest and CometKiwi, as baselines on our dataset. Furthermore, our experiments show that using a small subset of the proposed dataset containing 300 sentences to fine-tune Transquest, can improve its performance by more that 8{\%} in terms of the Pearson correlation with a held-out test set.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jafari-harandi-etal-2024-epoque-english">
<titleInfo>
<title>EPOQUE: An English-Persian Quality Estimation Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohammed</namePart>
<namePart type="given">Hossein</namePart>
<namePart type="family">Jafari Harandi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fatemeh</namePart>
<namePart type="family">Azadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Javad</namePart>
<namePart type="family">Dousti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heshaam</namePart>
<namePart type="family">Faili</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>Translation quality estimation (QE) is an important component in real-world machine translation applications. Unfortunately, human labeled QE datasets, which play an important role in developing and assessing QE models, are only available for limited language pairs. In this paper, we present the first English-Persian QE dataset, called EPOQUE, which has manually annotated direct assessment labels. EPOQUE contains 1000 sentences translated from English to Persian and annotated by three human annotators. It is publicly available, and thus can be used as a zero-shot test set, or for other scenarios in future work. We also evaluate and report the performance of two state-of-the-art QE models, i.e., Transquest and CometKiwi, as baselines on our dataset. Furthermore, our experiments show that using a small subset of the proposed dataset containing 300 sentences to fine-tune Transquest, can improve its performance by more that 8% in terms of the Pearson correlation with a held-out test set.</abstract>
<identifier type="citekey">jafari-harandi-etal-2024-epoque-english</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.550</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>6228</start>
<end>6235</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T EPOQUE: An English-Persian Quality Estimation Dataset
%A Jafari Harandi, Mohammed Hossein
%A Azadi, Fatemeh
%A Dousti, Mohammad Javad
%A Faili, Heshaam
%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 jafari-harandi-etal-2024-epoque-english
%X Translation quality estimation (QE) is an important component in real-world machine translation applications. Unfortunately, human labeled QE datasets, which play an important role in developing and assessing QE models, are only available for limited language pairs. In this paper, we present the first English-Persian QE dataset, called EPOQUE, which has manually annotated direct assessment labels. EPOQUE contains 1000 sentences translated from English to Persian and annotated by three human annotators. It is publicly available, and thus can be used as a zero-shot test set, or for other scenarios in future work. We also evaluate and report the performance of two state-of-the-art QE models, i.e., Transquest and CometKiwi, as baselines on our dataset. Furthermore, our experiments show that using a small subset of the proposed dataset containing 300 sentences to fine-tune Transquest, can improve its performance by more that 8% in terms of the Pearson correlation with a held-out test set.
%U https://aclanthology.org/2024.lrec-main.550
%P 6228-6235
Markdown (Informal)
[EPOQUE: An English-Persian Quality Estimation Dataset](https://aclanthology.org/2024.lrec-main.550) (Jafari Harandi et al., LREC-COLING 2024)
ACL
- Mohammed Hossein Jafari Harandi, Fatemeh Azadi, Mohammad Javad Dousti, and Heshaam Faili. 2024. EPOQUE: An English-Persian Quality Estimation Dataset. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 6228–6235, Torino, Italia. ELRA and ICCL.