@inproceedings{murauer-specht-2021-developing,
title = "Developing a Benchmark for Reducing Data Bias in Authorship Attribution",
author = {Murauer, Benjamin and
Specht, G{\"u}nther},
editor = "Gao, Yang and
Eger, Steffen and
Zhao, Wei and
Lertvittayakumjorn, Piyawat and
Fomicheva, Marina",
booktitle = "Proceedings of the 2nd Workshop on Evaluation and Comparison of NLP Systems",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.eval4nlp-1.18",
doi = "10.18653/v1/2021.eval4nlp-1.18",
pages = "179--188",
abstract = "Authorship attribution is the task of assigning an unknown document to an author from a set of candidates. In the past, studies in this field use various evaluation datasets to demonstrate the effectiveness of preprocessing steps, features, and models. However, only a small fraction of works use more than one dataset to prove claims. In this paper, we present a collection of highly diverse authorship attribution datasets, which better generalizes evaluation results from authorship attribution research. Furthermore, we implement a wide variety of previously used machine learning models and show that many approaches show vastly different performances when applied to different datasets. We include pre-trained language models, for the first time testing them in this field in a systematic way. Finally, we propose a set of aggregated scores to evaluate different aspects of the dataset collection.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="murauer-specht-2021-developing">
<titleInfo>
<title>Developing a Benchmark for Reducing Data Bias in Authorship Attribution</title>
</titleInfo>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="family">Murauer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Günther</namePart>
<namePart type="family">Specht</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Evaluation and Comparison of NLP Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steffen</namePart>
<namePart type="family">Eger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piyawat</namePart>
<namePart type="family">Lertvittayakumjorn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marina</namePart>
<namePart type="family">Fomicheva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Authorship attribution is the task of assigning an unknown document to an author from a set of candidates. In the past, studies in this field use various evaluation datasets to demonstrate the effectiveness of preprocessing steps, features, and models. However, only a small fraction of works use more than one dataset to prove claims. In this paper, we present a collection of highly diverse authorship attribution datasets, which better generalizes evaluation results from authorship attribution research. Furthermore, we implement a wide variety of previously used machine learning models and show that many approaches show vastly different performances when applied to different datasets. We include pre-trained language models, for the first time testing them in this field in a systematic way. Finally, we propose a set of aggregated scores to evaluate different aspects of the dataset collection.</abstract>
<identifier type="citekey">murauer-specht-2021-developing</identifier>
<identifier type="doi">10.18653/v1/2021.eval4nlp-1.18</identifier>
<location>
<url>https://aclanthology.org/2021.eval4nlp-1.18</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>179</start>
<end>188</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Developing a Benchmark for Reducing Data Bias in Authorship Attribution
%A Murauer, Benjamin
%A Specht, Günther
%Y Gao, Yang
%Y Eger, Steffen
%Y Zhao, Wei
%Y Lertvittayakumjorn, Piyawat
%Y Fomicheva, Marina
%S Proceedings of the 2nd Workshop on Evaluation and Comparison of NLP Systems
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F murauer-specht-2021-developing
%X Authorship attribution is the task of assigning an unknown document to an author from a set of candidates. In the past, studies in this field use various evaluation datasets to demonstrate the effectiveness of preprocessing steps, features, and models. However, only a small fraction of works use more than one dataset to prove claims. In this paper, we present a collection of highly diverse authorship attribution datasets, which better generalizes evaluation results from authorship attribution research. Furthermore, we implement a wide variety of previously used machine learning models and show that many approaches show vastly different performances when applied to different datasets. We include pre-trained language models, for the first time testing them in this field in a systematic way. Finally, we propose a set of aggregated scores to evaluate different aspects of the dataset collection.
%R 10.18653/v1/2021.eval4nlp-1.18
%U https://aclanthology.org/2021.eval4nlp-1.18
%U https://doi.org/10.18653/v1/2021.eval4nlp-1.18
%P 179-188
Markdown (Informal)
[Developing a Benchmark for Reducing Data Bias in Authorship Attribution](https://aclanthology.org/2021.eval4nlp-1.18) (Murauer & Specht, Eval4NLP 2021)
ACL