@inproceedings{guderlei-assenmacher-2020-evaluating,
title = "Evaluating Unsupervised Representation Learning for Detecting Stances of Fake News",
author = "Guderlei, Maike and
A{\ss}enmacher, Matthias",
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.558/",
doi = "10.18653/v1/2020.coling-main.558",
pages = "6339--6349",
abstract = "Our goal is to evaluate the usefulness of unsupervised representation learning techniques for detecting stances of Fake News. Therefore we examine several pre-trained language models with respect to their performance on two Fake News related data sets, both consisting of instances with a headline, an associated news article and the stance of the article towards the respective headline. Specifically, the aim is to understand how much hyperparameter tuning is necessary when fine-tuning the pre-trained architectures, how well transfer learning works in this specific case of stance detection and how sensitive the models are to changes in hyperparameters like batch size, learning rate (schedule), sequence length as well as the freezing technique. The results indicate that the computationally more expensive autoregression approach of XLNet (Yanget al., 2019) is outperformed by BERT-based models, notably by RoBERTa (Liu et al., 2019).While the learning rate seems to be the most important hyperparameter, experiments with different freezing techniques indicate that all evaluated architectures had already learned powerful language representations that pose a good starting point for fine-tuning them."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guderlei-assenmacher-2020-evaluating">
<titleInfo>
<title>Evaluating Unsupervised Representation Learning for Detecting Stances of Fake News</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maike</namePart>
<namePart type="family">Guderlei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthias</namePart>
<namePart type="family">Aßenmacher</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>Our goal is to evaluate the usefulness of unsupervised representation learning techniques for detecting stances of Fake News. Therefore we examine several pre-trained language models with respect to their performance on two Fake News related data sets, both consisting of instances with a headline, an associated news article and the stance of the article towards the respective headline. Specifically, the aim is to understand how much hyperparameter tuning is necessary when fine-tuning the pre-trained architectures, how well transfer learning works in this specific case of stance detection and how sensitive the models are to changes in hyperparameters like batch size, learning rate (schedule), sequence length as well as the freezing technique. The results indicate that the computationally more expensive autoregression approach of XLNet (Yanget al., 2019) is outperformed by BERT-based models, notably by RoBERTa (Liu et al., 2019).While the learning rate seems to be the most important hyperparameter, experiments with different freezing techniques indicate that all evaluated architectures had already learned powerful language representations that pose a good starting point for fine-tuning them.</abstract>
<identifier type="citekey">guderlei-assenmacher-2020-evaluating</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.558</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.558/</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>6339</start>
<end>6349</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Unsupervised Representation Learning for Detecting Stances of Fake News
%A Guderlei, Maike
%A Aßenmacher, Matthias
%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 guderlei-assenmacher-2020-evaluating
%X Our goal is to evaluate the usefulness of unsupervised representation learning techniques for detecting stances of Fake News. Therefore we examine several pre-trained language models with respect to their performance on two Fake News related data sets, both consisting of instances with a headline, an associated news article and the stance of the article towards the respective headline. Specifically, the aim is to understand how much hyperparameter tuning is necessary when fine-tuning the pre-trained architectures, how well transfer learning works in this specific case of stance detection and how sensitive the models are to changes in hyperparameters like batch size, learning rate (schedule), sequence length as well as the freezing technique. The results indicate that the computationally more expensive autoregression approach of XLNet (Yanget al., 2019) is outperformed by BERT-based models, notably by RoBERTa (Liu et al., 2019).While the learning rate seems to be the most important hyperparameter, experiments with different freezing techniques indicate that all evaluated architectures had already learned powerful language representations that pose a good starting point for fine-tuning them.
%R 10.18653/v1/2020.coling-main.558
%U https://aclanthology.org/2020.coling-main.558/
%U https://doi.org/10.18653/v1/2020.coling-main.558
%P 6339-6349
Markdown (Informal)
[Evaluating Unsupervised Representation Learning for Detecting Stances of Fake News](https://aclanthology.org/2020.coling-main.558/) (Guderlei & Aßenmacher, COLING 2020)
ACL