Combination of abstractive and extractive approaches for summarization of long scientific texts

In this research work, we present a method to generate summaries of long scientific documents that uses the advantages of both extractive and abstractive approaches. Before producing a summary in an abstractive manner, we perform the extractive step, which then is used for conditioning the abstracto...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Tretyak, Vladislav, Stepanov, Denis
Format:	Artikel
Sprache:	eng
Schlagworte:	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	Tretyak, Vladislav Stepanov, Denis
description	In this research work, we present a method to generate summaries of long scientific documents that uses the advantages of both extractive and abstractive approaches. Before producing a summary in an abstractive manner, we perform the extractive step, which then is used for conditioning the abstractor module. We used pre-trained transformer-based language models, for both extractor and abstractor. Our experiments showed that using extractive and abstractive models jointly significantly improves summarization results and ROUGE scores.
doi_str_mv	10.48550/arxiv.2006.05354
format	Article
fullrecord	<record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2006_05354</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2006_05354</sourcerecordid><originalsourceid>FETCH-LOGICAL-a674-11aed2d1094929eeb2a7604f7659f5ea8931e8157b23ec4338b93eda5745bf2d3</originalsourceid><addsrcrecordid>eNpFj8tOwzAURL1hURU-oKv6BxL8TOIlinhJldh0H10n12CpsSPbVIWvpxQEq9EszmgOIRvOatVpzW4hnfyxFow1NdNSqxUZ-jhbH6D4GGh0FGwuCcbij0ghTBRP_3VZUoTxDTN1MdH8Ps-Q_OcfeojhlebRYyje-ZGWM5uvyZWDQ8ab31yT_cP9vn-qdi-Pz_3droKmVRXngJOYODPKCINoBbQNU65ttHEaoTOSY8d1a4XEUUnZWSNxAt0qbZ2Y5Jpsf2YvhsOS_Pnbx_BtOlxM5RdtI1BH</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Combination of abstractive and extractive approaches for summarization of long scientific texts</title><source>arXiv.org</source><creator>Tretyak, Vladislav ; Stepanov, Denis</creator><creatorcontrib>Tretyak, Vladislav ; Stepanov, Denis</creatorcontrib><description>In this research work, we present a method to generate summaries of long scientific documents that uses the advantages of both extractive and abstractive approaches. Before producing a summary in an abstractive manner, we perform the extractive step, which then is used for conditioning the abstractor module. We used pre-trained transformer-based language models, for both extractor and abstractor. Our experiments showed that using extractive and abstractive models jointly significantly improves summarization results and ROUGE scores.</description><identifier>DOI: 10.48550/arxiv.2006.05354</identifier><language>eng</language><subject>Computer Science - Computation and Language</subject><creationdate>2020-06</creationdate><rights>http://creativecommons.org/publicdomain/zero/1.0</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/2006.05354$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2006.05354$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Tretyak, Vladislav</creatorcontrib><creatorcontrib>Stepanov, Denis</creatorcontrib><title>Combination of abstractive and extractive approaches for summarization of long scientific texts</title><description>In this research work, we present a method to generate summaries of long scientific documents that uses the advantages of both extractive and abstractive approaches. Before producing a summary in an abstractive manner, we perform the extractive step, which then is used for conditioning the abstractor module. We used pre-trained transformer-based language models, for both extractor and abstractor. Our experiments showed that using extractive and abstractive models jointly significantly improves summarization results and ROUGE scores.</description><subject>Computer Science - Computation and Language</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNpFj8tOwzAURL1hURU-oKv6BxL8TOIlinhJldh0H10n12CpsSPbVIWvpxQEq9EszmgOIRvOatVpzW4hnfyxFow1NdNSqxUZ-jhbH6D4GGh0FGwuCcbij0ghTBRP_3VZUoTxDTN1MdH8Ps-Q_OcfeojhlebRYyje-ZGWM5uvyZWDQ8ab31yT_cP9vn-qdi-Pz_3droKmVRXngJOYODPKCINoBbQNU65ttHEaoTOSY8d1a4XEUUnZWSNxAt0qbZ2Y5Jpsf2YvhsOS_Pnbx_BtOlxM5RdtI1BH</recordid><startdate>20200609</startdate><enddate>20200609</enddate><creator>Tretyak, Vladislav</creator><creator>Stepanov, Denis</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20200609</creationdate><title>Combination of abstractive and extractive approaches for summarization of long scientific texts</title><author>Tretyak, Vladislav ; Stepanov, Denis</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a674-11aed2d1094929eeb2a7604f7659f5ea8931e8157b23ec4338b93eda5745bf2d3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Computer Science - Computation and Language</topic><toplevel>online_resources</toplevel><creatorcontrib>Tretyak, Vladislav</creatorcontrib><creatorcontrib>Stepanov, Denis</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Tretyak, Vladislav</au><au>Stepanov, Denis</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Combination of abstractive and extractive approaches for summarization of long scientific texts</atitle><date>2020-06-09</date><risdate>2020</risdate><abstract>In this research work, we present a method to generate summaries of long scientific documents that uses the advantages of both extractive and abstractive approaches. Before producing a summary in an abstractive manner, we perform the extractive step, which then is used for conditioning the abstractor module. We used pre-trained transformer-based language models, for both extractor and abstractor. Our experiments showed that using extractive and abstractive models jointly significantly improves summarization results and ROUGE scores.</abstract><doi>10.48550/arxiv.2006.05354</doi><oa>free_for_read</oa></addata></record>
fulltext	fulltext_linktorsrc
identifier	DOI: 10.48550/arxiv.2006.05354
ispartof
issn
language	eng
recordid	cdi_arxiv_primary_2006_05354
source	arXiv.org
subjects	Computer Science - Computation and Language
title	Combination of abstractive and extractive approaches for summarization of long scientific texts
url	https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T03%3A28%3A01IST&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=Combination%20of%20abstractive%20and%20extractive%20approaches%20for%20summarization%20of%20long%20scientific%20texts&rft.au=Tretyak,%20Vladislav&rft.date=2020-06-09&rft_id=info:doi/10.48550/arxiv.2006.05354&rft_dat=%3Carxiv_GOX%3E2006_05354%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