@inproceedings{silva-etal-2023-authorship,
title = "Authorship Attribution of Late 19th Century Novels using {GAN}-{BERT}",
author = "Silva, Kanishka and
Can, Burcu and
Blain, Fr{\'e}d{\'e}ric and
Sarwar, Raheem and
Ugolini, Laura and
Mitkov, Ruslan",
editor = "Padmakumar, Vishakh and
Vallejo, Gisela and
Fu, Yao",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-srw.44",
doi = "10.18653/v1/2023.acl-srw.44",
pages = "310--320",
abstract = "Authorship attribution aims to identify the author of an anonymous text. The task becomes even more worthwhile when it comes to literary works. For example, pen names were commonly used by female authors in the 19th century resulting in some literary works being incorrectly attributed or claimed. With this motivation, we collated a dataset of late 19th century novels in English. Due to the imbalance in the dataset and the unavailability of enough data per author, we employed the GANBERT model along with data sampling strategies to fine-tune a transformer-based model for authorship attribution. Differently from the earlier studies on the GAN-BERT model, we conducted transfer learning on comparatively smaller author subsets to train more focused author-specific models yielding performance over 0.88 accuracy and F1 scores. Furthermore, we observed that increasing the sample size has a negative impact on the model{'}s performance. Our research mainly contributes to the ongoing authorship attribution research using GAN-BERT architecture, especially in attributing disputed novelists in the late 19th century.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="silva-etal-2023-authorship">
<titleInfo>
<title>Authorship Attribution of Late 19th Century Novels using GAN-BERT</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kanishka</namePart>
<namePart type="family">Silva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Burcu</namePart>
<namePart type="family">Can</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Blain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raheem</namePart>
<namePart type="family">Sarwar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="family">Ugolini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vishakh</namePart>
<namePart type="family">Padmakumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gisela</namePart>
<namePart type="family">Vallejo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yao</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Authorship attribution aims to identify the author of an anonymous text. The task becomes even more worthwhile when it comes to literary works. For example, pen names were commonly used by female authors in the 19th century resulting in some literary works being incorrectly attributed or claimed. With this motivation, we collated a dataset of late 19th century novels in English. Due to the imbalance in the dataset and the unavailability of enough data per author, we employed the GANBERT model along with data sampling strategies to fine-tune a transformer-based model for authorship attribution. Differently from the earlier studies on the GAN-BERT model, we conducted transfer learning on comparatively smaller author subsets to train more focused author-specific models yielding performance over 0.88 accuracy and F1 scores. Furthermore, we observed that increasing the sample size has a negative impact on the model’s performance. Our research mainly contributes to the ongoing authorship attribution research using GAN-BERT architecture, especially in attributing disputed novelists in the late 19th century.</abstract>
<identifier type="citekey">silva-etal-2023-authorship</identifier>
<identifier type="doi">10.18653/v1/2023.acl-srw.44</identifier>
<location>
<url>https://aclanthology.org/2023.acl-srw.44</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>310</start>
<end>320</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Authorship Attribution of Late 19th Century Novels using GAN-BERT
%A Silva, Kanishka
%A Can, Burcu
%A Blain, Frédéric
%A Sarwar, Raheem
%A Ugolini, Laura
%A Mitkov, Ruslan
%Y Padmakumar, Vishakh
%Y Vallejo, Gisela
%Y Fu, Yao
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F silva-etal-2023-authorship
%X Authorship attribution aims to identify the author of an anonymous text. The task becomes even more worthwhile when it comes to literary works. For example, pen names were commonly used by female authors in the 19th century resulting in some literary works being incorrectly attributed or claimed. With this motivation, we collated a dataset of late 19th century novels in English. Due to the imbalance in the dataset and the unavailability of enough data per author, we employed the GANBERT model along with data sampling strategies to fine-tune a transformer-based model for authorship attribution. Differently from the earlier studies on the GAN-BERT model, we conducted transfer learning on comparatively smaller author subsets to train more focused author-specific models yielding performance over 0.88 accuracy and F1 scores. Furthermore, we observed that increasing the sample size has a negative impact on the model’s performance. Our research mainly contributes to the ongoing authorship attribution research using GAN-BERT architecture, especially in attributing disputed novelists in the late 19th century.
%R 10.18653/v1/2023.acl-srw.44
%U https://aclanthology.org/2023.acl-srw.44
%U https://doi.org/10.18653/v1/2023.acl-srw.44
%P 310-320
Markdown (Informal)
[Authorship Attribution of Late 19th Century Novels using GAN-BERT](https://aclanthology.org/2023.acl-srw.44) (Silva et al., ACL 2023)
ACL
- Kanishka Silva, Burcu Can, Frédéric Blain, Raheem Sarwar, Laura Ugolini, and Ruslan Mitkov. 2023. Authorship Attribution of Late 19th Century Novels using GAN-BERT. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop), pages 310–320, Toronto, Canada. Association for Computational Linguistics.