@inproceedings{fang-etal-2022-pseudoreasoner,
title = "{P}seudo{R}easoner: Leveraging Pseudo Labels for Commonsense Knowledge Base Population",
author = "Fang, Tianqing and
Do, Quyet V. and
Zhang, Hongming and
Song, Yangqiu and
Wong, Ginny Y. and
See, Simon",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.246",
doi = "10.18653/v1/2022.findings-emnlp.246",
pages = "3379--3394",
abstract = "Commonsense Knowledge Base (CSKB) Population aims at reasoning over unseen entities and assertions on CSKBs, and is an important yet hard commonsense reasoning task. One challenge is that it requires out-of-domain generalization ability as the source CSKB for training is of a relatively smaller scale (1M) while the whole candidate space for population is way larger (200M). We propose PseudoReasoner, a semi-supervised learning framework for CSKB population that uses a teacher model pre-trained on CSKBs to provide pseudo labels on the unlabeled candidate dataset for a student model to learn from. The teacher can be a generative model rather than restricted to discriminative models as previous works.In addition, we design a new filtering procedure for pseudo labels based on influence function and the student model{'}s prediction to further improve the performance. The framework can improve the backbone model KG-BERT (RoBERTa-large) by 3.3 points on the overall performance and especially, 5.3 points on the out-of-domain performance, and achieves the state-of-the-art. The codes will be made public on acceptance. Codes and data are available at https://github.com/HKUST-KnowComp/PseudoReasoner.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fang-etal-2022-pseudoreasoner">
<titleInfo>
<title>PseudoReasoner: Leveraging Pseudo Labels for Commonsense Knowledge Base Population</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tianqing</namePart>
<namePart type="family">Fang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Quyet</namePart>
<namePart type="given">V</namePart>
<namePart type="family">Do</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongming</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yangqiu</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ginny</namePart>
<namePart type="given">Y</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">See</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>Findings of the Association for Computational Linguistics: EMNLP 2022</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 Base (CSKB) Population aims at reasoning over unseen entities and assertions on CSKBs, and is an important yet hard commonsense reasoning task. One challenge is that it requires out-of-domain generalization ability as the source CSKB for training is of a relatively smaller scale (1M) while the whole candidate space for population is way larger (200M). We propose PseudoReasoner, a semi-supervised learning framework for CSKB population that uses a teacher model pre-trained on CSKBs to provide pseudo labels on the unlabeled candidate dataset for a student model to learn from. The teacher can be a generative model rather than restricted to discriminative models as previous works.In addition, we design a new filtering procedure for pseudo labels based on influence function and the student model’s prediction to further improve the performance. The framework can improve the backbone model KG-BERT (RoBERTa-large) by 3.3 points on the overall performance and especially, 5.3 points on the out-of-domain performance, and achieves the state-of-the-art. The codes will be made public on acceptance. Codes and data are available at https://github.com/HKUST-KnowComp/PseudoReasoner.</abstract>
<identifier type="citekey">fang-etal-2022-pseudoreasoner</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.246</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.246</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>3379</start>
<end>3394</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PseudoReasoner: Leveraging Pseudo Labels for Commonsense Knowledge Base Population
%A Fang, Tianqing
%A Do, Quyet V.
%A Zhang, Hongming
%A Song, Yangqiu
%A Wong, Ginny Y.
%A See, Simon
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F fang-etal-2022-pseudoreasoner
%X Commonsense Knowledge Base (CSKB) Population aims at reasoning over unseen entities and assertions on CSKBs, and is an important yet hard commonsense reasoning task. One challenge is that it requires out-of-domain generalization ability as the source CSKB for training is of a relatively smaller scale (1M) while the whole candidate space for population is way larger (200M). We propose PseudoReasoner, a semi-supervised learning framework for CSKB population that uses a teacher model pre-trained on CSKBs to provide pseudo labels on the unlabeled candidate dataset for a student model to learn from. The teacher can be a generative model rather than restricted to discriminative models as previous works.In addition, we design a new filtering procedure for pseudo labels based on influence function and the student model’s prediction to further improve the performance. The framework can improve the backbone model KG-BERT (RoBERTa-large) by 3.3 points on the overall performance and especially, 5.3 points on the out-of-domain performance, and achieves the state-of-the-art. The codes will be made public on acceptance. Codes and data are available at https://github.com/HKUST-KnowComp/PseudoReasoner.
%R 10.18653/v1/2022.findings-emnlp.246
%U https://aclanthology.org/2022.findings-emnlp.246
%U https://doi.org/10.18653/v1/2022.findings-emnlp.246
%P 3379-3394
Markdown (Informal)
[PseudoReasoner: Leveraging Pseudo Labels for Commonsense Knowledge Base Population](https://aclanthology.org/2022.findings-emnlp.246) (Fang et al., Findings 2022)
ACL