Federated Named Entity Recognition

Federated Named Entity Recognition

We present an analysis of the performance of Federated Learning in a paradigmatic natural-language processing task: Named-Entity Recognition (NER). For our evaluation, we use the language-independent CoNLL-2003 dataset as our benchmark dataset and a Bi-LSTM-CRF model as our benchmark NER model. We s...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Mathew, Joel, Stripelis, Dimitris, Ambite, José Luis
Format: Artikel
Sprache:eng
Schlagworte:
Computer Science - Artificial Intelligence
Computer Science - Computation and Language
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Mathew, Joel
Stripelis, Dimitris
Ambite, José Luis
description We present an analysis of the performance of Federated Learning in a paradigmatic natural-language processing task: Named-Entity Recognition (NER). For our evaluation, we use the language-independent CoNLL-2003 dataset as our benchmark dataset and a Bi-LSTM-CRF model as our benchmark NER model. We show that federated training reaches almost the same performance as the centralized model, though with some performance degradation as the learning environments become more heterogeneous. We also show the convergence rate of federated models for NER. Finally, we discuss existing challenges of Federated Learning for NLP applications that can foster future research directions.
doi_str_mv 10.48550/arxiv.2203.15101
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2203_15101</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2203_15101</sourcerecordid><originalsourceid>FETCH-LOGICAL-a671-556065786d020ec89475d47c82101a1a24bafbd70d2e2ff32b63eb2147a637233</originalsourceid><addsrcrecordid>eNotzr0KwjAUBeAsDqI-gJPi3prc_DpKaVUoCuJebptEAtpKLaJvr1aXc7ZzPkKmjMbCSEmX2D7DIwagPGaSUTYki8xZ12Ln7HyP10-mdRe61_zoquZchy409ZgMPF7ubvLvETll6SnZRvlhs0vWeYRKs0hKRZXURlkK1FVmJbS0QlcGPj_IEESJvrSaWnDgPYdScVcCExoV18D5iMx-sz2yuLXhiu2r-GKLHsvfv7o3eQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Federated Named Entity Recognition</title><source>arXiv.org</source><creator>Mathew, Joel ; Stripelis, Dimitris ; Ambite, José Luis</creator><creatorcontrib>Mathew, Joel ; Stripelis, Dimitris ; Ambite, José Luis</creatorcontrib><description>We present an analysis of the performance of Federated Learning in a paradigmatic natural-language processing task: Named-Entity Recognition (NER). For our evaluation, we use the language-independent CoNLL-2003 dataset as our benchmark dataset and a Bi-LSTM-CRF model as our benchmark NER model. We show that federated training reaches almost the same performance as the centralized model, though with some performance degradation as the learning environments become more heterogeneous. We also show the convergence rate of federated models for NER. Finally, we discuss existing challenges of Federated Learning for NLP applications that can foster future research directions.</description><identifier>DOI: 10.48550/arxiv.2203.15101</identifier><language>eng</language><subject>Computer Science - Artificial Intelligence ; Computer Science - Computation and Language</subject><creationdate>2022-03</creationdate><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2203.15101$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2203.15101$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Mathew, Joel</creatorcontrib><creatorcontrib>Stripelis, Dimitris</creatorcontrib><creatorcontrib>Ambite, José Luis</creatorcontrib><title>Federated Named Entity Recognition</title><description>We present an analysis of the performance of Federated Learning in a paradigmatic natural-language processing task: Named-Entity Recognition (NER). For our evaluation, we use the language-independent CoNLL-2003 dataset as our benchmark dataset and a Bi-LSTM-CRF model as our benchmark NER model. We show that federated training reaches almost the same performance as the centralized model, though with some performance degradation as the learning environments become more heterogeneous. We also show the convergence rate of federated models for NER. Finally, we discuss existing challenges of Federated Learning for NLP applications that can foster future research directions.</description><subject>Computer Science - Artificial Intelligence</subject><subject>Computer Science - Computation and Language</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotzr0KwjAUBeAsDqI-gJPi3prc_DpKaVUoCuJebptEAtpKLaJvr1aXc7ZzPkKmjMbCSEmX2D7DIwagPGaSUTYki8xZ12Ln7HyP10-mdRe61_zoquZchy409ZgMPF7ubvLvETll6SnZRvlhs0vWeYRKs0hKRZXURlkK1FVmJbS0QlcGPj_IEESJvrSaWnDgPYdScVcCExoV18D5iMx-sz2yuLXhiu2r-GKLHsvfv7o3eQ</recordid><startdate>20220328</startdate><enddate>20220328</enddate><creator>Mathew, Joel</creator><creator>Stripelis, Dimitris</creator><creator>Ambite, José Luis</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20220328</creationdate><title>Federated Named Entity Recognition</title><author>Mathew, Joel ; Stripelis, Dimitris ; Ambite, José Luis</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a671-556065786d020ec89475d47c82101a1a24bafbd70d2e2ff32b63eb2147a637233</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Computer Science - Artificial Intelligence</topic><topic>Computer Science - Computation and Language</topic><toplevel>online_resources</toplevel><creatorcontrib>Mathew, Joel</creatorcontrib><creatorcontrib>Stripelis, Dimitris</creatorcontrib><creatorcontrib>Ambite, José Luis</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Mathew, Joel</au><au>Stripelis, Dimitris</au><au>Ambite, José Luis</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Federated Named Entity Recognition</atitle><date>2022-03-28</date><risdate>2022</risdate><abstract>We present an analysis of the performance of Federated Learning in a paradigmatic natural-language processing task: Named-Entity Recognition (NER). For our evaluation, we use the language-independent CoNLL-2003 dataset as our benchmark dataset and a Bi-LSTM-CRF model as our benchmark NER model. We show that federated training reaches almost the same performance as the centralized model, though with some performance degradation as the learning environments become more heterogeneous. We also show the convergence rate of federated models for NER. Finally, we discuss existing challenges of Federated Learning for NLP applications that can foster future research directions.</abstract><doi>10.48550/arxiv.2203.15101</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2203.15101
ispartof
issn
language eng
recordid cdi_arxiv_primary_2203_15101
source arXiv.org
subjects Computer Science - Artificial Intelligence
Computer Science - Computation and Language
title Federated Named Entity Recognition
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-26T12%3A23%3A41IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Federated%20Named%20Entity%20Recognition&rft.au=Mathew,%20Joel&rft.date=2022-03-28&rft_id=info:doi/10.48550/arxiv.2203.15101&rft_dat=%3Carxiv_GOX%3E2203_15101%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true