@inproceedings{hathurusinghe-etal-2021-privacy,
title = "A Privacy-Preserving Approach to Extraction of Personal Information through Automatic Annotation and Federated Learning",
author = "Hathurusinghe, Rajitha and
Nejadgholi, Isar and
Bolic, Miodrag",
editor = "Feyisetan, Oluwaseyi and
Ghanavati, Sepideh and
Malmasi, Shervin and
Thaine, Patricia",
booktitle = "Proceedings of the Third Workshop on Privacy in Natural Language Processing",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.privatenlp-1.5",
doi = "10.18653/v1/2021.privatenlp-1.5",
pages = "36--45",
abstract = "We curated WikiPII, an automatically labeled dataset composed of Wikipedia biography pages, annotated for personal information extraction. Although automatic annotation can lead to a high degree of label noise, it is an inexpensive process and can generate large volumes of annotated documents. We trained a BERT-based NER model with WikiPII and showed that with an adequately large training dataset, the model can significantly decrease the cost of manual information extraction, despite the high level of label noise. In a similar approach, organizations can leverage text mining techniques to create customized annotated datasets from their historical data without sharing the raw data for human annotation. Also, we explore collaborative training of NER models through federated learning when the annotation is noisy. Our results suggest that depending on the level of trust to the ML operator and the volume of the available data, distributed training can be an effective way of training a personal information identifier in a privacy-preserved manner. Research material is available at \url{https://github.com/ratmcu/wikipiifed}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hathurusinghe-etal-2021-privacy">
<titleInfo>
<title>A Privacy-Preserving Approach to Extraction of Personal Information through Automatic Annotation and Federated Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rajitha</namePart>
<namePart type="family">Hathurusinghe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isar</namePart>
<namePart type="family">Nejadgholi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miodrag</namePart>
<namePart type="family">Bolic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Privacy in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Oluwaseyi</namePart>
<namePart type="family">Feyisetan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sepideh</namePart>
<namePart type="family">Ghanavati</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shervin</namePart>
<namePart type="family">Malmasi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patricia</namePart>
<namePart type="family">Thaine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We curated WikiPII, an automatically labeled dataset composed of Wikipedia biography pages, annotated for personal information extraction. Although automatic annotation can lead to a high degree of label noise, it is an inexpensive process and can generate large volumes of annotated documents. We trained a BERT-based NER model with WikiPII and showed that with an adequately large training dataset, the model can significantly decrease the cost of manual information extraction, despite the high level of label noise. In a similar approach, organizations can leverage text mining techniques to create customized annotated datasets from their historical data without sharing the raw data for human annotation. Also, we explore collaborative training of NER models through federated learning when the annotation is noisy. Our results suggest that depending on the level of trust to the ML operator and the volume of the available data, distributed training can be an effective way of training a personal information identifier in a privacy-preserved manner. Research material is available at https://github.com/ratmcu/wikipiifed.</abstract>
<identifier type="citekey">hathurusinghe-etal-2021-privacy</identifier>
<identifier type="doi">10.18653/v1/2021.privatenlp-1.5</identifier>
<location>
<url>https://aclanthology.org/2021.privatenlp-1.5</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>36</start>
<end>45</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Privacy-Preserving Approach to Extraction of Personal Information through Automatic Annotation and Federated Learning
%A Hathurusinghe, Rajitha
%A Nejadgholi, Isar
%A Bolic, Miodrag
%Y Feyisetan, Oluwaseyi
%Y Ghanavati, Sepideh
%Y Malmasi, Shervin
%Y Thaine, Patricia
%S Proceedings of the Third Workshop on Privacy in Natural Language Processing
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F hathurusinghe-etal-2021-privacy
%X We curated WikiPII, an automatically labeled dataset composed of Wikipedia biography pages, annotated for personal information extraction. Although automatic annotation can lead to a high degree of label noise, it is an inexpensive process and can generate large volumes of annotated documents. We trained a BERT-based NER model with WikiPII and showed that with an adequately large training dataset, the model can significantly decrease the cost of manual information extraction, despite the high level of label noise. In a similar approach, organizations can leverage text mining techniques to create customized annotated datasets from their historical data without sharing the raw data for human annotation. Also, we explore collaborative training of NER models through federated learning when the annotation is noisy. Our results suggest that depending on the level of trust to the ML operator and the volume of the available data, distributed training can be an effective way of training a personal information identifier in a privacy-preserved manner. Research material is available at https://github.com/ratmcu/wikipiifed.
%R 10.18653/v1/2021.privatenlp-1.5
%U https://aclanthology.org/2021.privatenlp-1.5
%U https://doi.org/10.18653/v1/2021.privatenlp-1.5
%P 36-45
Markdown (Informal)
[A Privacy-Preserving Approach to Extraction of Personal Information through Automatic Annotation and Federated Learning](https://aclanthology.org/2021.privatenlp-1.5) (Hathurusinghe et al., PrivateNLP 2021)
ACL