@inproceedings{wang-etal-2023-federated,
title = "Federated Domain Adaptation for Named Entity Recognition via Distilling with Heterogeneous Tag Sets",
author = "Wang, Rui and
Yu, Tong and
Wu, Junda and
Zhao, Handong and
Kim, Sungchul and
Zhang, Ruiyi and
Mitra, Subrata and
Henao, Ricardo",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.470",
doi = "10.18653/v1/2023.findings-acl.470",
pages = "7449--7463",
abstract = "Federated learning involves collaborative training with private data from multiple platforms, while not violating data privacy. We study the problem of federated domain adaptation for Named Entity Recognition (NER), where we seek to transfer knowledge across different platforms with data of multiple domains. In addition, we consider a practical and challenging scenario, where NER datasets of different platforms of federated learning are annotated with heterogeneous tag sets, i.e., different sets of entity types. The goal is to train a global model with federated learning, such that it can predict with a complete tag set, i.e., with all the occurring entity types for data across all platforms. To cope with the heterogeneous tag sets in a multi-domain setting, we propose a distillation approach along with a mechanism of instance weighting to facilitate knowledge transfer across platforms. Besides, we release two re-annotated clinic NER datasets, for testing the proposed method in the clinic domain. Our method shows superior empirical performance for NER with federated learning.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2023-federated">
<titleInfo>
<title>Federated Domain Adaptation for Named Entity Recognition via Distilling with Heterogeneous Tag Sets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junda</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Handong</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sungchul</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruiyi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Subrata</namePart>
<namePart type="family">Mitra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ricardo</namePart>
<namePart type="family">Henao</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>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</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>Federated learning involves collaborative training with private data from multiple platforms, while not violating data privacy. We study the problem of federated domain adaptation for Named Entity Recognition (NER), where we seek to transfer knowledge across different platforms with data of multiple domains. In addition, we consider a practical and challenging scenario, where NER datasets of different platforms of federated learning are annotated with heterogeneous tag sets, i.e., different sets of entity types. The goal is to train a global model with federated learning, such that it can predict with a complete tag set, i.e., with all the occurring entity types for data across all platforms. To cope with the heterogeneous tag sets in a multi-domain setting, we propose a distillation approach along with a mechanism of instance weighting to facilitate knowledge transfer across platforms. Besides, we release two re-annotated clinic NER datasets, for testing the proposed method in the clinic domain. Our method shows superior empirical performance for NER with federated learning.</abstract>
<identifier type="citekey">wang-etal-2023-federated</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.470</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.470</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>7449</start>
<end>7463</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Federated Domain Adaptation for Named Entity Recognition via Distilling with Heterogeneous Tag Sets
%A Wang, Rui
%A Yu, Tong
%A Wu, Junda
%A Zhao, Handong
%A Kim, Sungchul
%A Zhang, Ruiyi
%A Mitra, Subrata
%A Henao, Ricardo
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F wang-etal-2023-federated
%X Federated learning involves collaborative training with private data from multiple platforms, while not violating data privacy. We study the problem of federated domain adaptation for Named Entity Recognition (NER), where we seek to transfer knowledge across different platforms with data of multiple domains. In addition, we consider a practical and challenging scenario, where NER datasets of different platforms of federated learning are annotated with heterogeneous tag sets, i.e., different sets of entity types. The goal is to train a global model with federated learning, such that it can predict with a complete tag set, i.e., with all the occurring entity types for data across all platforms. To cope with the heterogeneous tag sets in a multi-domain setting, we propose a distillation approach along with a mechanism of instance weighting to facilitate knowledge transfer across platforms. Besides, we release two re-annotated clinic NER datasets, for testing the proposed method in the clinic domain. Our method shows superior empirical performance for NER with federated learning.
%R 10.18653/v1/2023.findings-acl.470
%U https://aclanthology.org/2023.findings-acl.470
%U https://doi.org/10.18653/v1/2023.findings-acl.470
%P 7449-7463
Markdown (Informal)
[Federated Domain Adaptation for Named Entity Recognition via Distilling with Heterogeneous Tag Sets](https://aclanthology.org/2023.findings-acl.470) (Wang et al., Findings 2023)
ACL
- Rui Wang, Tong Yu, Junda Wu, Handong Zhao, Sungchul Kim, Ruiyi Zhang, Subrata Mitra, and Ricardo Henao. 2023. Federated Domain Adaptation for Named Entity Recognition via Distilling with Heterogeneous Tag Sets. In Findings of the Association for Computational Linguistics: ACL 2023, pages 7449–7463, Toronto, Canada. Association for Computational Linguistics.