@inproceedings{maharana-bansal-2022-grada-graph,
title = "{G}ra{DA}: Graph Generative Data Augmentation for Commonsense Reasoning",
author = "Maharana, Adyasha and
Bansal, Mohit",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.397/",
pages = "4499--4516",
abstract = "Recent advances in commonsense reasoning have been fueled by the availability of large-scale human annotated datasets. Manual annotation of such datasets, many of which are based on existing knowledge bases, is expensive and not scalable. Moreover, it is challenging to build augmentation data for commonsense reasoning because the synthetic questions need to adhere to real-world scenarios. Hence, we present GraDA, a graph-generative data augmentation framework to synthesize factual data samples from knowledge graphs for commonsense reasoning datasets. First, we train a graph-to-text model for conditional generation of questions from graph entities and relations. Then, we train a generator with GAN loss to generate distractors for synthetic questions. Our approach improves performance for SocialIQA, CODAH, HellaSwag and CommonsenseQA, and works well for generative tasks like ProtoQA. We show improvement in robustness to semantic adversaries after training with GraDA and provide human evaluation of the quality of synthetic datasets in terms of factuality and answerability. Our work provides evidence and encourages future research into graph-based generative data augmentation."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="maharana-bansal-2022-grada-graph">
<titleInfo>
<title>GraDA: Graph Generative Data Augmentation for Commonsense Reasoning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Adyasha</namePart>
<namePart type="family">Maharana</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</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">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</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>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent advances in commonsense reasoning have been fueled by the availability of large-scale human annotated datasets. Manual annotation of such datasets, many of which are based on existing knowledge bases, is expensive and not scalable. Moreover, it is challenging to build augmentation data for commonsense reasoning because the synthetic questions need to adhere to real-world scenarios. Hence, we present GraDA, a graph-generative data augmentation framework to synthesize factual data samples from knowledge graphs for commonsense reasoning datasets. First, we train a graph-to-text model for conditional generation of questions from graph entities and relations. Then, we train a generator with GAN loss to generate distractors for synthetic questions. Our approach improves performance for SocialIQA, CODAH, HellaSwag and CommonsenseQA, and works well for generative tasks like ProtoQA. We show improvement in robustness to semantic adversaries after training with GraDA and provide human evaluation of the quality of synthetic datasets in terms of factuality and answerability. Our work provides evidence and encourages future research into graph-based generative data augmentation.</abstract>
<identifier type="citekey">maharana-bansal-2022-grada-graph</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.397/</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>4499</start>
<end>4516</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GraDA: Graph Generative Data Augmentation for Commonsense Reasoning
%A Maharana, Adyasha
%A Bansal, Mohit
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F maharana-bansal-2022-grada-graph
%X Recent advances in commonsense reasoning have been fueled by the availability of large-scale human annotated datasets. Manual annotation of such datasets, many of which are based on existing knowledge bases, is expensive and not scalable. Moreover, it is challenging to build augmentation data for commonsense reasoning because the synthetic questions need to adhere to real-world scenarios. Hence, we present GraDA, a graph-generative data augmentation framework to synthesize factual data samples from knowledge graphs for commonsense reasoning datasets. First, we train a graph-to-text model for conditional generation of questions from graph entities and relations. Then, we train a generator with GAN loss to generate distractors for synthetic questions. Our approach improves performance for SocialIQA, CODAH, HellaSwag and CommonsenseQA, and works well for generative tasks like ProtoQA. We show improvement in robustness to semantic adversaries after training with GraDA and provide human evaluation of the quality of synthetic datasets in terms of factuality and answerability. Our work provides evidence and encourages future research into graph-based generative data augmentation.
%U https://aclanthology.org/2022.coling-1.397/
%P 4499-4516
Markdown (Informal)
[GraDA: Graph Generative Data Augmentation for Commonsense Reasoning](https://aclanthology.org/2022.coling-1.397/) (Maharana & Bansal, COLING 2022)
ACL