@inproceedings{jamali-etal-2022-percqa,
title = "{P}er{CQA}: {P}ersian Community Question Answering Dataset",
author = "Jamali, Naghme and
Yaghoobzadeh, Yadollah and
Faili, Heshaam",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.654",
pages = "6083--6092",
abstract = "Community Question Answering (CQA) forums provide answers to many real-life questions. These forums are trendy among machine learning researchers due to their large size. Automatic answer selection, answer ranking, question retrieval, expert finding, and fact-checking are example learning tasks performed using CQA data. This paper presents PerCQA, the first Persian dataset for CQA. This dataset contains the questions and answers crawled from the most well-known Persian forum. After data acquisition, we provide rigorous annotation guidelines in an iterative process and then the annotation of question-answer pairs in SemEvalCQA format. PerCQA contains 989 questions and 21,915 annotated answers. We make PerCQA publicly available to encourage more research in Persian CQA. We also build strong benchmarks for the task of answer selection in PerCQA by using mono- and multi-lingual pre-trained language models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jamali-etal-2022-percqa">
<titleInfo>
<title>PerCQA: Persian Community Question Answering Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Naghme</namePart>
<namePart type="family">Jamali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yadollah</namePart>
<namePart type="family">Yaghoobzadeh</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>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Community Question Answering (CQA) forums provide answers to many real-life questions. These forums are trendy among machine learning researchers due to their large size. Automatic answer selection, answer ranking, question retrieval, expert finding, and fact-checking are example learning tasks performed using CQA data. This paper presents PerCQA, the first Persian dataset for CQA. This dataset contains the questions and answers crawled from the most well-known Persian forum. After data acquisition, we provide rigorous annotation guidelines in an iterative process and then the annotation of question-answer pairs in SemEvalCQA format. PerCQA contains 989 questions and 21,915 annotated answers. We make PerCQA publicly available to encourage more research in Persian CQA. We also build strong benchmarks for the task of answer selection in PerCQA by using mono- and multi-lingual pre-trained language models.</abstract>
<identifier type="citekey">jamali-etal-2022-percqa</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.654</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>6083</start>
<end>6092</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PerCQA: Persian Community Question Answering Dataset
%A Jamali, Naghme
%A Yaghoobzadeh, Yadollah
%A Faili, Heshaam
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F jamali-etal-2022-percqa
%X Community Question Answering (CQA) forums provide answers to many real-life questions. These forums are trendy among machine learning researchers due to their large size. Automatic answer selection, answer ranking, question retrieval, expert finding, and fact-checking are example learning tasks performed using CQA data. This paper presents PerCQA, the first Persian dataset for CQA. This dataset contains the questions and answers crawled from the most well-known Persian forum. After data acquisition, we provide rigorous annotation guidelines in an iterative process and then the annotation of question-answer pairs in SemEvalCQA format. PerCQA contains 989 questions and 21,915 annotated answers. We make PerCQA publicly available to encourage more research in Persian CQA. We also build strong benchmarks for the task of answer selection in PerCQA by using mono- and multi-lingual pre-trained language models.
%U https://aclanthology.org/2022.lrec-1.654
%P 6083-6092
Markdown (Informal)
[PerCQA: Persian Community Question Answering Dataset](https://aclanthology.org/2022.lrec-1.654) (Jamali et al., LREC 2022)
ACL
- Naghme Jamali, Yadollah Yaghoobzadeh, and Heshaam Faili. 2022. PerCQA: Persian Community Question Answering Dataset. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 6083–6092, Marseille, France. European Language Resources Association.