NLPDove at SemEval-2020 Task 12: Improving Offensive Language Detection with Cross-lingual Transfer
This paper describes our approach to the task of identifying offensive languages in a multilingual setting. We investigate two data augmentation strategies: using additional semi-supervised labels with different thresholds and cross-lingual transfer with data selection. Leveraging the semi-supervise...
Gespeichert in:
Veröffentlicht in: | arXiv.org 2020-08 |
---|---|
Hauptverfasser: | , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | |
container_title | arXiv.org |
container_volume | |
creator | Ahn, Hwijeen Sun, Jimin Chan Young Park Seo, Jungyun |
description | This paper describes our approach to the task of identifying offensive languages in a multilingual setting. We investigate two data augmentation strategies: using additional semi-supervised labels with different thresholds and cross-lingual transfer with data selection. Leveraging the semi-supervised dataset resulted in performance improvements compared to the baseline trained solely with the manually-annotated dataset. We propose a new metric, Translation Embedding Distance, to measure the transferability of instances for cross-lingual data selection. We also introduce various preprocessing steps tailored for social media text along with methods to fine-tune the pre-trained multilingual BERT (mBERT) for offensive language identification. Our multilingual systems achieved competitive results in Greek, Danish, and Turkish at OffensEval 2020. |
format | Article |
fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2430535067</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2430535067</sourcerecordid><originalsourceid>FETCH-proquest_journals_24305350673</originalsourceid><addsrcrecordid>eNqNjMsKwjAQAIMgKNp_WPBcSDetilcfKBQV7F2CbGu0JppN6-9bwQ_wNIcZpieGqFQSz1PEgYiYb1JKnM4wy9RQXPb5ceVaAh3gRI91q-sYJUooNN8hwQXsHk_vWmMrOJQlWTZdnGtbNboiWFGgSzDOwtuEKyy9Y45r87U1FF5bLsmPRb_UNVP040hMNutiuY278ashDueba7zt1BlTJTOVyelM_Vd9AGRRQ_A</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2430535067</pqid></control><display><type>article</type><title>NLPDove at SemEval-2020 Task 12: Improving Offensive Language Detection with Cross-lingual Transfer</title><source>Free E- Journals</source><creator>Ahn, Hwijeen ; Sun, Jimin ; Chan Young Park ; Seo, Jungyun</creator><creatorcontrib>Ahn, Hwijeen ; Sun, Jimin ; Chan Young Park ; Seo, Jungyun</creatorcontrib><description>This paper describes our approach to the task of identifying offensive languages in a multilingual setting. We investigate two data augmentation strategies: using additional semi-supervised labels with different thresholds and cross-lingual transfer with data selection. Leveraging the semi-supervised dataset resulted in performance improvements compared to the baseline trained solely with the manually-annotated dataset. We propose a new metric, Translation Embedding Distance, to measure the transferability of instances for cross-lingual data selection. We also introduce various preprocessing steps tailored for social media text along with methods to fine-tune the pre-trained multilingual BERT (mBERT) for offensive language identification. Our multilingual systems achieved competitive results in Greek, Danish, and Turkish at OffensEval 2020.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Datasets ; Digital media ; Identification methods ; Multilingual systems ; Multilingualism</subject><ispartof>arXiv.org, 2020-08</ispartof><rights>2020. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</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>780,784</link.rule.ids></links><search><creatorcontrib>Ahn, Hwijeen</creatorcontrib><creatorcontrib>Sun, Jimin</creatorcontrib><creatorcontrib>Chan Young Park</creatorcontrib><creatorcontrib>Seo, Jungyun</creatorcontrib><title>NLPDove at SemEval-2020 Task 12: Improving Offensive Language Detection with Cross-lingual Transfer</title><title>arXiv.org</title><description>This paper describes our approach to the task of identifying offensive languages in a multilingual setting. We investigate two data augmentation strategies: using additional semi-supervised labels with different thresholds and cross-lingual transfer with data selection. Leveraging the semi-supervised dataset resulted in performance improvements compared to the baseline trained solely with the manually-annotated dataset. We propose a new metric, Translation Embedding Distance, to measure the transferability of instances for cross-lingual data selection. We also introduce various preprocessing steps tailored for social media text along with methods to fine-tune the pre-trained multilingual BERT (mBERT) for offensive language identification. Our multilingual systems achieved competitive results in Greek, Danish, and Turkish at OffensEval 2020.</description><subject>Datasets</subject><subject>Digital media</subject><subject>Identification methods</subject><subject>Multilingual systems</subject><subject>Multilingualism</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNjMsKwjAQAIMgKNp_WPBcSDetilcfKBQV7F2CbGu0JppN6-9bwQ_wNIcZpieGqFQSz1PEgYiYb1JKnM4wy9RQXPb5ceVaAh3gRI91q-sYJUooNN8hwQXsHk_vWmMrOJQlWTZdnGtbNboiWFGgSzDOwtuEKyy9Y45r87U1FF5bLsmPRb_UNVP040hMNutiuY278ashDueba7zt1BlTJTOVyelM_Vd9AGRRQ_A</recordid><startdate>20200804</startdate><enddate>20200804</enddate><creator>Ahn, Hwijeen</creator><creator>Sun, Jimin</creator><creator>Chan Young Park</creator><creator>Seo, Jungyun</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20200804</creationdate><title>NLPDove at SemEval-2020 Task 12: Improving Offensive Language Detection with Cross-lingual Transfer</title><author>Ahn, Hwijeen ; Sun, Jimin ; Chan Young Park ; Seo, Jungyun</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_24305350673</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Datasets</topic><topic>Digital media</topic><topic>Identification methods</topic><topic>Multilingual systems</topic><topic>Multilingualism</topic><toplevel>online_resources</toplevel><creatorcontrib>Ahn, Hwijeen</creatorcontrib><creatorcontrib>Sun, Jimin</creatorcontrib><creatorcontrib>Chan Young Park</creatorcontrib><creatorcontrib>Seo, Jungyun</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Access via ProQuest (Open Access)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Ahn, Hwijeen</au><au>Sun, Jimin</au><au>Chan Young Park</au><au>Seo, Jungyun</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>NLPDove at SemEval-2020 Task 12: Improving Offensive Language Detection with Cross-lingual Transfer</atitle><jtitle>arXiv.org</jtitle><date>2020-08-04</date><risdate>2020</risdate><eissn>2331-8422</eissn><abstract>This paper describes our approach to the task of identifying offensive languages in a multilingual setting. We investigate two data augmentation strategies: using additional semi-supervised labels with different thresholds and cross-lingual transfer with data selection. Leveraging the semi-supervised dataset resulted in performance improvements compared to the baseline trained solely with the manually-annotated dataset. We propose a new metric, Translation Embedding Distance, to measure the transferability of instances for cross-lingual data selection. We also introduce various preprocessing steps tailored for social media text along with methods to fine-tune the pre-trained multilingual BERT (mBERT) for offensive language identification. Our multilingual systems achieved competitive results in Greek, Danish, and Turkish at OffensEval 2020.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | EISSN: 2331-8422 |
ispartof | arXiv.org, 2020-08 |
issn | 2331-8422 |
language | eng |
recordid | cdi_proquest_journals_2430535067 |
source | Free E- Journals |
subjects | Datasets Digital media Identification methods Multilingual systems Multilingualism |
title | NLPDove at SemEval-2020 Task 12: Improving Offensive Language Detection with Cross-lingual Transfer |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-04T05%3A23%3A04IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=NLPDove%20at%20SemEval-2020%20Task%2012:%20Improving%20Offensive%20Language%20Detection%20with%20Cross-lingual%20Transfer&rft.jtitle=arXiv.org&rft.au=Ahn,%20Hwijeen&rft.date=2020-08-04&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2430535067%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2430535067&rft_id=info:pmid/&rfr_iscdi=true |