@inproceedings{wang-etal-2022-cn,
title = "{CN}-{A}uto{MIC}: Distilling {C}hinese Commonsense Knowledge from Pretrained Language Models",
author = "Wang, Chenhao and
Li, Jiachun and
Chen, Yubo and
Liu, Kang and
Zhao, Jun",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.628",
doi = "10.18653/v1/2022.emnlp-main.628",
pages = "9253--9265",
abstract = "Commonsense knowledge graphs (CKGs) are increasingly applied in various natural language processing tasks. However, most existing CKGs are limited to English, which hinders related research in non-English languages. Meanwhile, directly generating commonsense knowledge from pretrained language models has recently received attention, yet it has not been explored in non-English languages. In this paper, we propose a large-scale Chinese CKG generated from multilingual PLMs, named as **CN-AutoMIC**, aiming to fill the research gap of non-English CKGs. To improve the efficiency, we propose generate-by-category strategy to reduce invalid generation. To ensure the filtering quality, we develop cascaded filters to discard low-quality results. To further increase the diversity and density, we introduce a bootstrapping iteration process to reuse generated results. Finally, we conduct detailed analyses on CN-AutoMIC from different aspects. Empirical results show the proposed CKG has high quality and diversity, surpassing the direct translation version of similar English CKGs. We also find some interesting deficiency patterns and differences between relations, which reveal pending problems in commonsense knowledge generation. We share the resources and related models for further study.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2022-cn">
<titleInfo>
<title>CN-AutoMIC: Distilling Chinese Commonsense Knowledge from Pretrained Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chenhao</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiachun</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yubo</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Zhao</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 2022 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</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</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Commonsense knowledge graphs (CKGs) are increasingly applied in various natural language processing tasks. However, most existing CKGs are limited to English, which hinders related research in non-English languages. Meanwhile, directly generating commonsense knowledge from pretrained language models has recently received attention, yet it has not been explored in non-English languages. In this paper, we propose a large-scale Chinese CKG generated from multilingual PLMs, named as **CN-AutoMIC**, aiming to fill the research gap of non-English CKGs. To improve the efficiency, we propose generate-by-category strategy to reduce invalid generation. To ensure the filtering quality, we develop cascaded filters to discard low-quality results. To further increase the diversity and density, we introduce a bootstrapping iteration process to reuse generated results. Finally, we conduct detailed analyses on CN-AutoMIC from different aspects. Empirical results show the proposed CKG has high quality and diversity, surpassing the direct translation version of similar English CKGs. We also find some interesting deficiency patterns and differences between relations, which reveal pending problems in commonsense knowledge generation. We share the resources and related models for further study.</abstract>
<identifier type="citekey">wang-etal-2022-cn</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.628</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.628</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>9253</start>
<end>9265</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CN-AutoMIC: Distilling Chinese Commonsense Knowledge from Pretrained Language Models
%A Wang, Chenhao
%A Li, Jiachun
%A Chen, Yubo
%A Liu, Kang
%A Zhao, Jun
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F wang-etal-2022-cn
%X Commonsense knowledge graphs (CKGs) are increasingly applied in various natural language processing tasks. However, most existing CKGs are limited to English, which hinders related research in non-English languages. Meanwhile, directly generating commonsense knowledge from pretrained language models has recently received attention, yet it has not been explored in non-English languages. In this paper, we propose a large-scale Chinese CKG generated from multilingual PLMs, named as **CN-AutoMIC**, aiming to fill the research gap of non-English CKGs. To improve the efficiency, we propose generate-by-category strategy to reduce invalid generation. To ensure the filtering quality, we develop cascaded filters to discard low-quality results. To further increase the diversity and density, we introduce a bootstrapping iteration process to reuse generated results. Finally, we conduct detailed analyses on CN-AutoMIC from different aspects. Empirical results show the proposed CKG has high quality and diversity, surpassing the direct translation version of similar English CKGs. We also find some interesting deficiency patterns and differences between relations, which reveal pending problems in commonsense knowledge generation. We share the resources and related models for further study.
%R 10.18653/v1/2022.emnlp-main.628
%U https://aclanthology.org/2022.emnlp-main.628
%U https://doi.org/10.18653/v1/2022.emnlp-main.628
%P 9253-9265
Markdown (Informal)
[CN-AutoMIC: Distilling Chinese Commonsense Knowledge from Pretrained Language Models](https://aclanthology.org/2022.emnlp-main.628) (Wang et al., EMNLP 2022)
ACL