@inproceedings{safavi-etal-2021-negater,
title = "{N}egat{ER}: {U}nsupervised {D}iscovery of {N}egatives in {C}ommonsense {K}nowledge {B}ases",
author = "Safavi, Tara and
Zhu, Jing and
Koutra, Danai",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.456/",
doi = "10.18653/v1/2021.emnlp-main.456",
pages = "5633--5646",
abstract = "Codifying commonsense knowledge in machines is a longstanding goal of artificial intelligence. Recently, much progress toward this goal has been made with automatic knowledge base (KB) construction techniques. However, such techniques focus primarily on the acquisition of positive (true) KB statements, even though negative (false) statements are often also important for discriminative reasoning over commonsense KBs. As a first step toward the latter, this paper proposes NegatER, a framework that ranks potential negatives in commonsense KBs using a contextual language model (LM). Importantly, as most KBs do not contain negatives, NegatER relies only on the positive knowledge in the LM and does not require ground-truth negative examples. Experiments demonstrate that, compared to multiple contrastive data augmentation approaches, NegatER yields negatives that are more grammatical, coherent, and informative{---}leading to statistically significant accuracy improvements in a challenging KB completion task and confirming that the positive knowledge in LMs can be {\textquotedblleft}re-purposed{\textquotedblright} to generate negative knowledge."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="safavi-etal-2021-negater">
<titleInfo>
<title>NegatER: Unsupervised Discovery of Negatives in Commonsense Knowledge Bases</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tara</namePart>
<namePart type="family">Safavi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danai</namePart>
<namePart type="family">Koutra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Codifying commonsense knowledge in machines is a longstanding goal of artificial intelligence. Recently, much progress toward this goal has been made with automatic knowledge base (KB) construction techniques. However, such techniques focus primarily on the acquisition of positive (true) KB statements, even though negative (false) statements are often also important for discriminative reasoning over commonsense KBs. As a first step toward the latter, this paper proposes NegatER, a framework that ranks potential negatives in commonsense KBs using a contextual language model (LM). Importantly, as most KBs do not contain negatives, NegatER relies only on the positive knowledge in the LM and does not require ground-truth negative examples. Experiments demonstrate that, compared to multiple contrastive data augmentation approaches, NegatER yields negatives that are more grammatical, coherent, and informative—leading to statistically significant accuracy improvements in a challenging KB completion task and confirming that the positive knowledge in LMs can be “re-purposed” to generate negative knowledge.</abstract>
<identifier type="citekey">safavi-etal-2021-negater</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.456</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.456/</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>5633</start>
<end>5646</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NegatER: Unsupervised Discovery of Negatives in Commonsense Knowledge Bases
%A Safavi, Tara
%A Zhu, Jing
%A Koutra, Danai
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F safavi-etal-2021-negater
%X Codifying commonsense knowledge in machines is a longstanding goal of artificial intelligence. Recently, much progress toward this goal has been made with automatic knowledge base (KB) construction techniques. However, such techniques focus primarily on the acquisition of positive (true) KB statements, even though negative (false) statements are often also important for discriminative reasoning over commonsense KBs. As a first step toward the latter, this paper proposes NegatER, a framework that ranks potential negatives in commonsense KBs using a contextual language model (LM). Importantly, as most KBs do not contain negatives, NegatER relies only on the positive knowledge in the LM and does not require ground-truth negative examples. Experiments demonstrate that, compared to multiple contrastive data augmentation approaches, NegatER yields negatives that are more grammatical, coherent, and informative—leading to statistically significant accuracy improvements in a challenging KB completion task and confirming that the positive knowledge in LMs can be “re-purposed” to generate negative knowledge.
%R 10.18653/v1/2021.emnlp-main.456
%U https://aclanthology.org/2021.emnlp-main.456/
%U https://doi.org/10.18653/v1/2021.emnlp-main.456
%P 5633-5646
Markdown (Informal)
[NegatER: Unsupervised Discovery of Negatives in Commonsense Knowledge Bases](https://aclanthology.org/2021.emnlp-main.456/) (Safavi et al., EMNLP 2021)
ACL