MIDAS at SemEval-2020 Task 10: Emphasis Selection using Label Distribution Learning and Contextual Embeddings

This paper presents our submission to the SemEval 2020 - Task 10 on emphasis selection in written text. We approach this emphasis selection problem as a sequence labeling task where we represent the underlying text with various contextual embedding models. We also employ label distribution learning...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	arXiv.org 2020-09
Hauptverfasser:	Sarthak Anand, Gupta, Pradyumna, Yadav, Hemant, Mahata, Debanjan, Gosangi, Rakesh, Zhang, Haimin, Shah, Rajiv Ratn
Format:	Artikel
Sprache:	eng
Schlagworte:	Learning
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	Sarthak Anand Gupta, Pradyumna Yadav, Hemant Mahata, Debanjan Gosangi, Rakesh Zhang, Haimin Shah, Rajiv Ratn
description	This paper presents our submission to the SemEval 2020 - Task 10 on emphasis selection in written text. We approach this emphasis selection problem as a sequence labeling task where we represent the underlying text with various contextual embedding models. We also employ label distribution learning to account for annotator disagreements. We experiment with the choice of model architectures, trainability of layers, and different contextual embeddings. Our best performing architecture is an ensemble of different models, which achieved an overall matching score of 0.783, placing us 15th out of 31 participating teams. Lastly, we analyze the results in terms of parts of speech tags, sentence lengths, and word ordering.
format	Article
fullrecord	<record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2440759498</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2440759498</sourcerecordid><originalsourceid>FETCH-proquest_journals_24407594983</originalsourceid><addsrcrecordid>eNqNzMEKgkAUheEhCJLqHS60FsZR09qFGQW2qn1cc6qpcSzvTPT4WfQArc7iO_w95okwDPw0EmLAxkRXzrmYJiKOQ4_V281ysQO0sJN1_kTtCy447JFuEPA55PX9gqSoYy2PVjUGHClzhgJLqWGpyLaqdF8oJLbmY2gqyBpj5cs61F2jlFXVAY1Y_4Sa5Pi3QzZZ5fts7d_b5uEk2cO1ca3p6CCiiCfxLJql4X-vNxpUR2s</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2440759498</pqid></control><display><type>article</type><title>MIDAS at SemEval-2020 Task 10: Emphasis Selection using Label Distribution Learning and Contextual Embeddings</title><source>Free E- Journals</source><creator>Sarthak Anand ; Gupta, Pradyumna ; Yadav, Hemant ; Mahata, Debanjan ; Gosangi, Rakesh ; Zhang, Haimin ; Shah, Rajiv Ratn</creator><creatorcontrib>Sarthak Anand ; Gupta, Pradyumna ; Yadav, Hemant ; Mahata, Debanjan ; Gosangi, Rakesh ; Zhang, Haimin ; Shah, Rajiv Ratn</creatorcontrib><description>This paper presents our submission to the SemEval 2020 - Task 10 on emphasis selection in written text. We approach this emphasis selection problem as a sequence labeling task where we represent the underlying text with various contextual embedding models. We also employ label distribution learning to account for annotator disagreements. We experiment with the choice of model architectures, trainability of layers, and different contextual embeddings. Our best performing architecture is an ensemble of different models, which achieved an overall matching score of 0.783, placing us 15th out of 31 participating teams. Lastly, we analyze the results in terms of parts of speech tags, sentence lengths, and word ordering.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Learning</subject><ispartof>arXiv.org, 2020-09</ispartof><rights>2020. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (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>776,780</link.rule.ids></links><search><creatorcontrib>Sarthak Anand</creatorcontrib><creatorcontrib>Gupta, Pradyumna</creatorcontrib><creatorcontrib>Yadav, Hemant</creatorcontrib><creatorcontrib>Mahata, Debanjan</creatorcontrib><creatorcontrib>Gosangi, Rakesh</creatorcontrib><creatorcontrib>Zhang, Haimin</creatorcontrib><creatorcontrib>Shah, Rajiv Ratn</creatorcontrib><title>MIDAS at SemEval-2020 Task 10: Emphasis Selection using Label Distribution Learning and Contextual Embeddings</title><title>arXiv.org</title><description>This paper presents our submission to the SemEval 2020 - Task 10 on emphasis selection in written text. We approach this emphasis selection problem as a sequence labeling task where we represent the underlying text with various contextual embedding models. We also employ label distribution learning to account for annotator disagreements. We experiment with the choice of model architectures, trainability of layers, and different contextual embeddings. Our best performing architecture is an ensemble of different models, which achieved an overall matching score of 0.783, placing us 15th out of 31 participating teams. Lastly, we analyze the results in terms of parts of speech tags, sentence lengths, and word ordering.</description><subject>Learning</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNqNzMEKgkAUheEhCJLqHS60FsZR09qFGQW2qn1cc6qpcSzvTPT4WfQArc7iO_w95okwDPw0EmLAxkRXzrmYJiKOQ4_V281ysQO0sJN1_kTtCy447JFuEPA55PX9gqSoYy2PVjUGHClzhgJLqWGpyLaqdF8oJLbmY2gqyBpj5cs61F2jlFXVAY1Y_4Sa5Pi3QzZZ5fts7d_b5uEk2cO1ca3p6CCiiCfxLJql4X-vNxpUR2s</recordid><startdate>20200906</startdate><enddate>20200906</enddate><creator>Sarthak Anand</creator><creator>Gupta, Pradyumna</creator><creator>Yadav, Hemant</creator><creator>Mahata, Debanjan</creator><creator>Gosangi, Rakesh</creator><creator>Zhang, Haimin</creator><creator>Shah, Rajiv Ratn</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>20200906</creationdate><title>MIDAS at SemEval-2020 Task 10: Emphasis Selection using Label Distribution Learning and Contextual Embeddings</title><author>Sarthak Anand ; Gupta, Pradyumna ; Yadav, Hemant ; Mahata, Debanjan ; Gosangi, Rakesh ; Zhang, Haimin ; Shah, Rajiv Ratn</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_24407594983</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Sarthak Anand</creatorcontrib><creatorcontrib>Gupta, Pradyumna</creatorcontrib><creatorcontrib>Yadav, Hemant</creatorcontrib><creatorcontrib>Mahata, Debanjan</creatorcontrib><creatorcontrib>Gosangi, Rakesh</creatorcontrib><creatorcontrib>Zhang, Haimin</creatorcontrib><creatorcontrib>Shah, Rajiv Ratn</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni)</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</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</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>Sarthak Anand</au><au>Gupta, Pradyumna</au><au>Yadav, Hemant</au><au>Mahata, Debanjan</au><au>Gosangi, Rakesh</au><au>Zhang, Haimin</au><au>Shah, Rajiv Ratn</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>MIDAS at SemEval-2020 Task 10: Emphasis Selection using Label Distribution Learning and Contextual Embeddings</atitle><jtitle>arXiv.org</jtitle><date>2020-09-06</date><risdate>2020</risdate><eissn>2331-8422</eissn><abstract>This paper presents our submission to the SemEval 2020 - Task 10 on emphasis selection in written text. We approach this emphasis selection problem as a sequence labeling task where we represent the underlying text with various contextual embedding models. We also employ label distribution learning to account for annotator disagreements. We experiment with the choice of model architectures, trainability of layers, and different contextual embeddings. Our best performing architecture is an ensemble of different models, which achieved an overall matching score of 0.783, placing us 15th out of 31 participating teams. Lastly, we analyze the results in terms of parts of speech tags, sentence lengths, and word ordering.</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, 2020-09
issn	2331-8422
language	eng
recordid	cdi_proquest_journals_2440759498
source	Free E- Journals
subjects	Learning
title	MIDAS at SemEval-2020 Task 10: Emphasis Selection using Label Distribution Learning and Contextual Embeddings
url	https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-11T22%3A48%3A51IST&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=MIDAS%20at%20SemEval-2020%20Task%2010:%20Emphasis%20Selection%20using%20Label%20Distribution%20Learning%20and%20Contextual%20Embeddings&rft.jtitle=arXiv.org&rft.au=Sarthak%20Anand&rft.date=2020-09-06&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2440759498%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2440759498&rft_id=info:pmid/&rfr_iscdi=true