@inproceedings{kim-choi-2020-unsupervised,
title = "Unsupervised Fact Checking by Counter-Weighted Positive and Negative Evidential Paths in A Knowledge Graph",
author = "Kim, Jiseong and
Choi, Key-sun",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.147",
doi = "10.18653/v1/2020.coling-main.147",
pages = "1677--1686",
abstract = "Misinformation spreads across media, community, and knowledge graphs in the Web by not only human agents but also information extraction algorithms that extract factual statements from unstructured textual data to populate the existing knowledge graphs. Traditional fact checking by experts or crowds is increasingly difficult to keep pace with the volume of newly created misinformation in the Web. Therefore, it is important and necessary to enhance the computational ability to determine whether a given factual statement is truthful or not. We view this problem as a truth scoring task in a knowledge graph. We present a novel rule-based approach that finds positive and negative evidential paths in a knowledge graph for a given factual statement and calculates a truth score for the given statement by unsupervised ensemble of the found positive and negative evidential paths. For example, we can determine the factual statement {``}United States is the birth place of Barack Obama{''} as truthful if there is the positive evidential path (Barack Obama, birthPlace, Hawaii) ∧ (Hawaii, country, United States) in a knowledge graph. For another example, we can determine the factual statement {``}Canada is the nationality of Barack Obama{''} as untruthful if there is the negative evidential path (Barack Obama, nationality, United States) ∧ (United States, {\mbox{$\neq$}}, Canada) in a knowledge graph. For evaluating on a real-world situation, we constructed an evaluation dataset by labeling truth or untruth label on factual statements that were extracted from Wikipedia texts by using the state-of-the-art BERT-based information extraction system. Our evaluation results show that our approach outperforms the state-of-the-art unsupervised approaches significantly by up to 0.12 AUC-ROC and even outperforms the supervised approach by up to 0.05 AUC-ROC not only in our dataset but also in the two different standard datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-choi-2020-unsupervised">
<titleInfo>
<title>Unsupervised Fact Checking by Counter-Weighted Positive and Negative Evidential Paths in A Knowledge Graph</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiseong</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Misinformation spreads across media, community, and knowledge graphs in the Web by not only human agents but also information extraction algorithms that extract factual statements from unstructured textual data to populate the existing knowledge graphs. Traditional fact checking by experts or crowds is increasingly difficult to keep pace with the volume of newly created misinformation in the Web. Therefore, it is important and necessary to enhance the computational ability to determine whether a given factual statement is truthful or not. We view this problem as a truth scoring task in a knowledge graph. We present a novel rule-based approach that finds positive and negative evidential paths in a knowledge graph for a given factual statement and calculates a truth score for the given statement by unsupervised ensemble of the found positive and negative evidential paths. For example, we can determine the factual statement “United States is the birth place of Barack Obama” as truthful if there is the positive evidential path (Barack Obama, birthPlace, Hawaii) ∧ (Hawaii, country, United States) in a knowledge graph. For another example, we can determine the factual statement “Canada is the nationality of Barack Obama” as untruthful if there is the negative evidential path (Barack Obama, nationality, United States) ∧ (United States, ʼneq, Canada) in a knowledge graph. For evaluating on a real-world situation, we constructed an evaluation dataset by labeling truth or untruth label on factual statements that were extracted from Wikipedia texts by using the state-of-the-art BERT-based information extraction system. Our evaluation results show that our approach outperforms the state-of-the-art unsupervised approaches significantly by up to 0.12 AUC-ROC and even outperforms the supervised approach by up to 0.05 AUC-ROC not only in our dataset but also in the two different standard datasets.</abstract>
<identifier type="citekey">kim-choi-2020-unsupervised</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.147</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.147</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>1677</start>
<end>1686</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unsupervised Fact Checking by Counter-Weighted Positive and Negative Evidential Paths in A Knowledge Graph
%A Kim, Jiseong
%A Choi, Key-sun
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F kim-choi-2020-unsupervised
%X Misinformation spreads across media, community, and knowledge graphs in the Web by not only human agents but also information extraction algorithms that extract factual statements from unstructured textual data to populate the existing knowledge graphs. Traditional fact checking by experts or crowds is increasingly difficult to keep pace with the volume of newly created misinformation in the Web. Therefore, it is important and necessary to enhance the computational ability to determine whether a given factual statement is truthful or not. We view this problem as a truth scoring task in a knowledge graph. We present a novel rule-based approach that finds positive and negative evidential paths in a knowledge graph for a given factual statement and calculates a truth score for the given statement by unsupervised ensemble of the found positive and negative evidential paths. For example, we can determine the factual statement “United States is the birth place of Barack Obama” as truthful if there is the positive evidential path (Barack Obama, birthPlace, Hawaii) ∧ (Hawaii, country, United States) in a knowledge graph. For another example, we can determine the factual statement “Canada is the nationality of Barack Obama” as untruthful if there is the negative evidential path (Barack Obama, nationality, United States) ∧ (United States, ʼneq, Canada) in a knowledge graph. For evaluating on a real-world situation, we constructed an evaluation dataset by labeling truth or untruth label on factual statements that were extracted from Wikipedia texts by using the state-of-the-art BERT-based information extraction system. Our evaluation results show that our approach outperforms the state-of-the-art unsupervised approaches significantly by up to 0.12 AUC-ROC and even outperforms the supervised approach by up to 0.05 AUC-ROC not only in our dataset but also in the two different standard datasets.
%R 10.18653/v1/2020.coling-main.147
%U https://aclanthology.org/2020.coling-main.147
%U https://doi.org/10.18653/v1/2020.coling-main.147
%P 1677-1686
Markdown (Informal)
[Unsupervised Fact Checking by Counter-Weighted Positive and Negative Evidential Paths in A Knowledge Graph](https://aclanthology.org/2020.coling-main.147) (Kim & Choi, COLING 2020)
ACL