@inproceedings{sawatphol-etal-2022-topic,
title = "Topic-Regularized Authorship Representation Learning",
author = "Sawatphol, Jitkapat and
Chaiwong, Nonthakit and
Udomcharoenchaikit, Can and
Nutanong, Sarana",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.70",
doi = "10.18653/v1/2022.emnlp-main.70",
pages = "1076--1082",
abstract = "Authorship attribution is a task that aims to identify the author of a given piece of writing. We aim to develop a generalized solution that can handle a large number of texts from authors and topics unavailable in training data. Previous studies have proposed strategies to address only either unseen authors or unseen topics. Authorship representation learning has been shown to work in open-set environments with a large number of unseen authors but has not been explicitly designed for cross-topic environments at the same time. To handle a large number of unseen authors and topics, we propose Authorship Representation Regularization (ARR), a distillation framework that creates authorship representation with reduced reliance on topic-specific information. To assess the performance of our framework, we also propose a cross-topic-open-set evaluation method. Our proposed method has improved performances in the cross-topic-open set setup over baselines in 4 out of 6 cases.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sawatphol-etal-2022-topic">
<titleInfo>
<title>Topic-Regularized Authorship Representation Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jitkapat</namePart>
<namePart type="family">Sawatphol</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nonthakit</namePart>
<namePart type="family">Chaiwong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Can</namePart>
<namePart type="family">Udomcharoenchaikit</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarana</namePart>
<namePart type="family">Nutanong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Authorship attribution is a task that aims to identify the author of a given piece of writing. We aim to develop a generalized solution that can handle a large number of texts from authors and topics unavailable in training data. Previous studies have proposed strategies to address only either unseen authors or unseen topics. Authorship representation learning has been shown to work in open-set environments with a large number of unseen authors but has not been explicitly designed for cross-topic environments at the same time. To handle a large number of unseen authors and topics, we propose Authorship Representation Regularization (ARR), a distillation framework that creates authorship representation with reduced reliance on topic-specific information. To assess the performance of our framework, we also propose a cross-topic-open-set evaluation method. Our proposed method has improved performances in the cross-topic-open set setup over baselines in 4 out of 6 cases.</abstract>
<identifier type="citekey">sawatphol-etal-2022-topic</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.70</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.70</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>1076</start>
<end>1082</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Topic-Regularized Authorship Representation Learning
%A Sawatphol, Jitkapat
%A Chaiwong, Nonthakit
%A Udomcharoenchaikit, Can
%A Nutanong, Sarana
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F sawatphol-etal-2022-topic
%X Authorship attribution is a task that aims to identify the author of a given piece of writing. We aim to develop a generalized solution that can handle a large number of texts from authors and topics unavailable in training data. Previous studies have proposed strategies to address only either unseen authors or unseen topics. Authorship representation learning has been shown to work in open-set environments with a large number of unseen authors but has not been explicitly designed for cross-topic environments at the same time. To handle a large number of unseen authors and topics, we propose Authorship Representation Regularization (ARR), a distillation framework that creates authorship representation with reduced reliance on topic-specific information. To assess the performance of our framework, we also propose a cross-topic-open-set evaluation method. Our proposed method has improved performances in the cross-topic-open set setup over baselines in 4 out of 6 cases.
%R 10.18653/v1/2022.emnlp-main.70
%U https://aclanthology.org/2022.emnlp-main.70
%U https://doi.org/10.18653/v1/2022.emnlp-main.70
%P 1076-1082
Markdown (Informal)
[Topic-Regularized Authorship Representation Learning](https://aclanthology.org/2022.emnlp-main.70) (Sawatphol et al., EMNLP 2022)
ACL
- Jitkapat Sawatphol, Nonthakit Chaiwong, Can Udomcharoenchaikit, and Sarana Nutanong. 2022. Topic-Regularized Authorship Representation Learning. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 1076–1082, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.