@inproceedings{lee-etal-2021-towards,
title = "Towards Few-shot Fact-Checking via Perplexity",
author = "Lee, Nayeon and
Bang, Yejin and
Madotto, Andrea and
Fung, Pascale",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.158",
doi = "10.18653/v1/2021.naacl-main.158",
pages = "1971--1981",
abstract = "Few-shot learning has drawn researchers{'} attention to overcome the problem of data scarcity. Recently, large pre-trained language models have shown great performance in few-shot learning for various downstream tasks, such as question answering and machine translation. Nevertheless, little exploration has been made to achieve few-shot learning for the fact-checking task. However, fact-checking is an important problem, especially when the amount of information online is growing exponentially every day. In this paper, we propose a new way of utilizing the powerful transfer learning ability of a language model via a perplexity score. The most notable strength of our methodology lies in its capability in few-shot learning. With only two training samples, our methodology can already outperform the Major Class baseline by more than an absolute 10{\%} on the F1-Macro metric across multiple datasets. Through experiments, we empirically verify the plausibility of the rather surprising usage of the perplexity score in the context of fact-checking and highlight the strength of our few-shot methodology by comparing it to strong fine-tuning-based baseline models. Moreover, we construct and publicly release two new fact-checking datasets related to COVID-19.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lee-etal-2021-towards">
<titleInfo>
<title>Towards Few-shot Fact-Checking via Perplexity</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nayeon</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yejin</namePart>
<namePart type="family">Bang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Madotto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pascale</namePart>
<namePart type="family">Fung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-jun</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Few-shot learning has drawn researchers’ attention to overcome the problem of data scarcity. Recently, large pre-trained language models have shown great performance in few-shot learning for various downstream tasks, such as question answering and machine translation. Nevertheless, little exploration has been made to achieve few-shot learning for the fact-checking task. However, fact-checking is an important problem, especially when the amount of information online is growing exponentially every day. In this paper, we propose a new way of utilizing the powerful transfer learning ability of a language model via a perplexity score. The most notable strength of our methodology lies in its capability in few-shot learning. With only two training samples, our methodology can already outperform the Major Class baseline by more than an absolute 10% on the F1-Macro metric across multiple datasets. Through experiments, we empirically verify the plausibility of the rather surprising usage of the perplexity score in the context of fact-checking and highlight the strength of our few-shot methodology by comparing it to strong fine-tuning-based baseline models. Moreover, we construct and publicly release two new fact-checking datasets related to COVID-19.</abstract>
<identifier type="citekey">lee-etal-2021-towards</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.158</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.158</url>
</location>
<part>
<date>2021-jun</date>
<extent unit="page">
<start>1971</start>
<end>1981</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Few-shot Fact-Checking via Perplexity
%A Lee, Nayeon
%A Bang, Yejin
%A Madotto, Andrea
%A Fung, Pascale
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 jun
%I Association for Computational Linguistics
%C Online
%F lee-etal-2021-towards
%X Few-shot learning has drawn researchers’ attention to overcome the problem of data scarcity. Recently, large pre-trained language models have shown great performance in few-shot learning for various downstream tasks, such as question answering and machine translation. Nevertheless, little exploration has been made to achieve few-shot learning for the fact-checking task. However, fact-checking is an important problem, especially when the amount of information online is growing exponentially every day. In this paper, we propose a new way of utilizing the powerful transfer learning ability of a language model via a perplexity score. The most notable strength of our methodology lies in its capability in few-shot learning. With only two training samples, our methodology can already outperform the Major Class baseline by more than an absolute 10% on the F1-Macro metric across multiple datasets. Through experiments, we empirically verify the plausibility of the rather surprising usage of the perplexity score in the context of fact-checking and highlight the strength of our few-shot methodology by comparing it to strong fine-tuning-based baseline models. Moreover, we construct and publicly release two new fact-checking datasets related to COVID-19.
%R 10.18653/v1/2021.naacl-main.158
%U https://aclanthology.org/2021.naacl-main.158
%U https://doi.org/10.18653/v1/2021.naacl-main.158
%P 1971-1981
Markdown (Informal)
[Towards Few-shot Fact-Checking via Perplexity](https://aclanthology.org/2021.naacl-main.158) (Lee et al., NAACL 2021)
ACL
- Nayeon Lee, Yejin Bang, Andrea Madotto, and Pascale Fung. 2021. Towards Few-shot Fact-Checking via Perplexity. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1971–1981, Online. Association for Computational Linguistics.