@inproceedings{pisarevskaya-shavrina-2022-wikiomnia,
title = "{W}iki{O}mnia: filtration and evaluation of the generated {QA} corpus on the whole {R}ussian {W}ikipedia",
author = "Pisarevskaya, Dina and
Shavrina, Tatiana",
editor = "Bosselut, Antoine and
Chandu, Khyathi and
Dhole, Kaustubh and
Gangal, Varun and
Gehrmann, Sebastian and
Jernite, Yacine and
Novikova, Jekaterina and
Perez-Beltrachini, Laura",
booktitle = "Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM)",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.gem-1.10",
doi = "10.18653/v1/2022.gem-1.10",
pages = "125--135",
abstract = "The General QA field has been developing the methodology referencing the Stanford Question answering dataset (SQuAD) as the significant benchmark. Compiling factual questions datasets requires manual annotations, limiting the training data{'}s potential size. We present the WikiOmnia dataset, a new publicly available set of QA pairs and corresponding Russian Wikipedia article summary sections, composed with a fully automated generation and filtration pipeline. To ensure high quality of generated QA pairs, diverse manual and automated evaluation techniques were applied. The WikiOmnia pipeline is available open-source and is also tested for creating SQuAD-formatted QA on other domains, like news texts, fiction, and social media. The resulting dataset includes two parts: raw data on the whole Russian Wikipedia (7,930,873 QA pairs with paragraphs for ruGPT-3 XL and 7,991,040 QA pairs with paragraphs for ruT5-large) and cleaned data with strict automatic verification (over 160,000 QA pairs with paragraphs for ruGPT-3 XL and over 3,400,000 QA pairs with paragraphs for ruT5-large).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pisarevskaya-shavrina-2022-wikiomnia">
<titleInfo>
<title>WikiOmnia: filtration and evaluation of the generated QA corpus on the whole Russian Wikipedia</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Pisarevskaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tatiana</namePart>
<namePart type="family">Shavrina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Antoine</namePart>
<namePart type="family">Bosselut</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khyathi</namePart>
<namePart type="family">Chandu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaustubh</namePart>
<namePart type="family">Dhole</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Varun</namePart>
<namePart type="family">Gangal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Gehrmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yacine</namePart>
<namePart type="family">Jernite</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jekaterina</namePart>
<namePart type="family">Novikova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="family">Perez-Beltrachini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The General QA field has been developing the methodology referencing the Stanford Question answering dataset (SQuAD) as the significant benchmark. Compiling factual questions datasets requires manual annotations, limiting the training data’s potential size. We present the WikiOmnia dataset, a new publicly available set of QA pairs and corresponding Russian Wikipedia article summary sections, composed with a fully automated generation and filtration pipeline. To ensure high quality of generated QA pairs, diverse manual and automated evaluation techniques were applied. The WikiOmnia pipeline is available open-source and is also tested for creating SQuAD-formatted QA on other domains, like news texts, fiction, and social media. The resulting dataset includes two parts: raw data on the whole Russian Wikipedia (7,930,873 QA pairs with paragraphs for ruGPT-3 XL and 7,991,040 QA pairs with paragraphs for ruT5-large) and cleaned data with strict automatic verification (over 160,000 QA pairs with paragraphs for ruGPT-3 XL and over 3,400,000 QA pairs with paragraphs for ruT5-large).</abstract>
<identifier type="citekey">pisarevskaya-shavrina-2022-wikiomnia</identifier>
<identifier type="doi">10.18653/v1/2022.gem-1.10</identifier>
<location>
<url>https://aclanthology.org/2022.gem-1.10</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>125</start>
<end>135</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T WikiOmnia: filtration and evaluation of the generated QA corpus on the whole Russian Wikipedia
%A Pisarevskaya, Dina
%A Shavrina, Tatiana
%Y Bosselut, Antoine
%Y Chandu, Khyathi
%Y Dhole, Kaustubh
%Y Gangal, Varun
%Y Gehrmann, Sebastian
%Y Jernite, Yacine
%Y Novikova, Jekaterina
%Y Perez-Beltrachini, Laura
%S Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM)
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Hybrid)
%F pisarevskaya-shavrina-2022-wikiomnia
%X The General QA field has been developing the methodology referencing the Stanford Question answering dataset (SQuAD) as the significant benchmark. Compiling factual questions datasets requires manual annotations, limiting the training data’s potential size. We present the WikiOmnia dataset, a new publicly available set of QA pairs and corresponding Russian Wikipedia article summary sections, composed with a fully automated generation and filtration pipeline. To ensure high quality of generated QA pairs, diverse manual and automated evaluation techniques were applied. The WikiOmnia pipeline is available open-source and is also tested for creating SQuAD-formatted QA on other domains, like news texts, fiction, and social media. The resulting dataset includes two parts: raw data on the whole Russian Wikipedia (7,930,873 QA pairs with paragraphs for ruGPT-3 XL and 7,991,040 QA pairs with paragraphs for ruT5-large) and cleaned data with strict automatic verification (over 160,000 QA pairs with paragraphs for ruGPT-3 XL and over 3,400,000 QA pairs with paragraphs for ruT5-large).
%R 10.18653/v1/2022.gem-1.10
%U https://aclanthology.org/2022.gem-1.10
%U https://doi.org/10.18653/v1/2022.gem-1.10
%P 125-135
Markdown (Informal)
[WikiOmnia: filtration and evaluation of the generated QA corpus on the whole Russian Wikipedia](https://aclanthology.org/2022.gem-1.10) (Pisarevskaya & Shavrina, GEM 2022)
ACL