@inproceedings{garcia-silva-etal-2019-empirical,
title = "An Empirical Study on Pre-trained Embeddings and Language Models for Bot Detection",
author = "Garcia-Silva, Andres and
Berrio, Cristian and
G{\'o}mez-P{\'e}rez, Jos{\'e} Manuel",
editor = "Augenstein, Isabelle and
Gella, Spandana and
Ruder, Sebastian and
Kann, Katharina and
Can, Burcu and
Welbl, Johannes and
Conneau, Alexis and
Ren, Xiang and
Rei, Marek",
booktitle = "Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019)",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-4317",
doi = "10.18653/v1/W19-4317",
pages = "148--155",
abstract = "Fine-tuning pre-trained language models has significantly advanced the state of art in a wide range of NLP downstream tasks. Usually, such language models are learned from large and well-formed text corpora from e.g. encyclopedic resources, books or news. However, a significant amount of the text to be analyzed nowadays is Web data, often from social media. In this paper we consider the research question: How do standard pre-trained language models generalize and capture the peculiarities of rather short, informal and frequently automatically generated text found in social media? To answer this question, we focus on bot detection in Twitter as our evaluation task and test the performance of fine-tuning approaches based on language models against popular neural architectures such as LSTM and CNN combined with pre-trained and contextualized embeddings. Our results also show strong performance variations among the different language model approaches, which suggest further research.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="garcia-silva-etal-2019-empirical">
<titleInfo>
<title>An Empirical Study on Pre-trained Embeddings and Language Models for Bot Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andres</namePart>
<namePart type="family">Garcia-Silva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cristian</namePart>
<namePart type="family">Berrio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">José</namePart>
<namePart type="given">Manuel</namePart>
<namePart type="family">Gómez-Pérez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Spandana</namePart>
<namePart type="family">Gella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Ruder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katharina</namePart>
<namePart type="family">Kann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Burcu</namePart>
<namePart type="family">Can</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johannes</namePart>
<namePart type="family">Welbl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Conneau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marek</namePart>
<namePart type="family">Rei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Fine-tuning pre-trained language models has significantly advanced the state of art in a wide range of NLP downstream tasks. Usually, such language models are learned from large and well-formed text corpora from e.g. encyclopedic resources, books or news. However, a significant amount of the text to be analyzed nowadays is Web data, often from social media. In this paper we consider the research question: How do standard pre-trained language models generalize and capture the peculiarities of rather short, informal and frequently automatically generated text found in social media? To answer this question, we focus on bot detection in Twitter as our evaluation task and test the performance of fine-tuning approaches based on language models against popular neural architectures such as LSTM and CNN combined with pre-trained and contextualized embeddings. Our results also show strong performance variations among the different language model approaches, which suggest further research.</abstract>
<identifier type="citekey">garcia-silva-etal-2019-empirical</identifier>
<identifier type="doi">10.18653/v1/W19-4317</identifier>
<location>
<url>https://aclanthology.org/W19-4317</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>148</start>
<end>155</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Empirical Study on Pre-trained Embeddings and Language Models for Bot Detection
%A Garcia-Silva, Andres
%A Berrio, Cristian
%A Gómez-Pérez, José Manuel
%Y Augenstein, Isabelle
%Y Gella, Spandana
%Y Ruder, Sebastian
%Y Kann, Katharina
%Y Can, Burcu
%Y Welbl, Johannes
%Y Conneau, Alexis
%Y Ren, Xiang
%Y Rei, Marek
%S Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019)
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence, Italy
%F garcia-silva-etal-2019-empirical
%X Fine-tuning pre-trained language models has significantly advanced the state of art in a wide range of NLP downstream tasks. Usually, such language models are learned from large and well-formed text corpora from e.g. encyclopedic resources, books or news. However, a significant amount of the text to be analyzed nowadays is Web data, often from social media. In this paper we consider the research question: How do standard pre-trained language models generalize and capture the peculiarities of rather short, informal and frequently automatically generated text found in social media? To answer this question, we focus on bot detection in Twitter as our evaluation task and test the performance of fine-tuning approaches based on language models against popular neural architectures such as LSTM and CNN combined with pre-trained and contextualized embeddings. Our results also show strong performance variations among the different language model approaches, which suggest further research.
%R 10.18653/v1/W19-4317
%U https://aclanthology.org/W19-4317
%U https://doi.org/10.18653/v1/W19-4317
%P 148-155
Markdown (Informal)
[An Empirical Study on Pre-trained Embeddings and Language Models for Bot Detection](https://aclanthology.org/W19-4317) (Garcia-Silva et al., RepL4NLP 2019)
ACL