@inproceedings{liu-etal-2020-adapting-open,
title = "Adapting Open Domain Fact Extraction and Verification to {COVID}-{FACT} through In-Domain Language Modeling",
author = "Liu, Zhenghao and
Xiong, Chenyan and
Dai, Zhuyun and
Sun, Si and
Sun, Maosong and
Liu, Zhiyuan",
editor = "Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.findings-emnlp.216",
doi = "10.18653/v1/2020.findings-emnlp.216",
pages = "2395--2400",
abstract = "With the epidemic of COVID-19, verifying the scientifically false online information, such as fake news and maliciously fabricated statements, has become crucial. However, the lack of training data in the scientific domain limits the performance of fact verification models. This paper proposes an in-domain language modeling method for fact extraction and verification systems. We come up with SciKGAT to combine the advantages of open-domain literature search, state-of-the-art fact verification systems and in-domain medical knowledge through language modeling. Our experiments on SCIFACT, a dataset of expert-written scientific fact verification, show that SciKGAT achieves 30{\%} absolute improvement on precision. Our analyses show that such improvement thrives from our in-domain language model by picking up more related evidence pieces and accurate fact verification. Our codes and data are released via Github.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2020-adapting-open">
<titleInfo>
<title>Adapting Open Domain Fact Extraction and Verification to COVID-FACT through In-Domain Language Modeling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhenghao</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenyan</namePart>
<namePart type="family">Xiong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhuyun</namePart>
<namePart type="family">Dai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Si</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maosong</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiyuan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
</titleInfo>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>With the epidemic of COVID-19, verifying the scientifically false online information, such as fake news and maliciously fabricated statements, has become crucial. However, the lack of training data in the scientific domain limits the performance of fact verification models. This paper proposes an in-domain language modeling method for fact extraction and verification systems. We come up with SciKGAT to combine the advantages of open-domain literature search, state-of-the-art fact verification systems and in-domain medical knowledge through language modeling. Our experiments on SCIFACT, a dataset of expert-written scientific fact verification, show that SciKGAT achieves 30% absolute improvement on precision. Our analyses show that such improvement thrives from our in-domain language model by picking up more related evidence pieces and accurate fact verification. Our codes and data are released via Github.</abstract>
<identifier type="citekey">liu-etal-2020-adapting-open</identifier>
<identifier type="doi">10.18653/v1/2020.findings-emnlp.216</identifier>
<location>
<url>https://aclanthology.org/2020.findings-emnlp.216</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>2395</start>
<end>2400</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Adapting Open Domain Fact Extraction and Verification to COVID-FACT through In-Domain Language Modeling
%A Liu, Zhenghao
%A Xiong, Chenyan
%A Dai, Zhuyun
%A Sun, Si
%A Sun, Maosong
%A Liu, Zhiyuan
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F liu-etal-2020-adapting-open
%X With the epidemic of COVID-19, verifying the scientifically false online information, such as fake news and maliciously fabricated statements, has become crucial. However, the lack of training data in the scientific domain limits the performance of fact verification models. This paper proposes an in-domain language modeling method for fact extraction and verification systems. We come up with SciKGAT to combine the advantages of open-domain literature search, state-of-the-art fact verification systems and in-domain medical knowledge through language modeling. Our experiments on SCIFACT, a dataset of expert-written scientific fact verification, show that SciKGAT achieves 30% absolute improvement on precision. Our analyses show that such improvement thrives from our in-domain language model by picking up more related evidence pieces and accurate fact verification. Our codes and data are released via Github.
%R 10.18653/v1/2020.findings-emnlp.216
%U https://aclanthology.org/2020.findings-emnlp.216
%U https://doi.org/10.18653/v1/2020.findings-emnlp.216
%P 2395-2400
Markdown (Informal)
[Adapting Open Domain Fact Extraction and Verification to COVID-FACT through In-Domain Language Modeling](https://aclanthology.org/2020.findings-emnlp.216) (Liu et al., Findings 2020)
ACL