Automating News Summarization with Sentence Vectors Offset

Text summaries consist of short versions of texts that convey their key aspects and help readers understand the gist of such texts without reading them in full. Generating such summaries is important for users who must sift through ever-increasing volumes of the content generated on the web. However...

Full description

Saved in:
Bibliographic Details
Main Authors: Steinert, Mauricio, Granada, Roger, Aires, Joao Paulo, Meneguzzi, Felipe
Format: Conference Proceeding
Language:English
Subjects:
automatic text summarization
Gold
information retrieval
Internet
Mathematical model
natural language processing
Neural networks
Semantics
Task analysis
word embedding
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 107
container_issue
container_start_page 102
container_title
container_volume
creator Steinert, Mauricio
Granada, Roger
Aires, Joao Paulo
Meneguzzi, Felipe
description Text summaries consist of short versions of texts that convey their key aspects and help readers understand the gist of such texts without reading them in full. Generating such summaries is important for users who must sift through ever-increasing volumes of the content generated on the web. However, generating high-quality summaries is time-consuming for humans and challenging for automated systems, since it involves understanding the semantics of the underlying texts in order to extract key information. In this work, we develop an extractive text summarization method using vector offsets, which we show empirically to be able to summarize texts from an Internet news corpus with an effectiveness competitive with state-of-the-art extractive techniques.
doi_str_mv 10.1109/BRACIS.2019.00027
format conference_proceeding
fullrecord <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_8924017</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>8924017</ieee_id><sourcerecordid>8924017</sourcerecordid><originalsourceid>FETCH-LOGICAL-i118t-16dc4a391f1eb7ca2b9bcf7f48e060088bee18e02bddbbd8e0ef60b77a5d36d53</originalsourceid><addsrcrecordid>eNotjt1KxDAUhKMguKx9APEmL9Cak7T58W4tui4sLlj1dkmaE63YVtosiz69Ab2Z-RiGYQi5BFYAMHN9-7SqN03BGZiCMcbVCcmM0qC4hpJXAk7JgstS5DLpOcnm-SPVBGeirKoFuVkd4tjb2A1v9BGPM20OfW-n7idF40CPXXynDQ4RhxbpK7ZxnGa6C2HGeEHOgv2cMfv3JXm5v3uuH_Ltbr2pV9u8A9AxB-nb0goDAdCp1nJnXBtUKDUyyZjWDhESc-e9cz4RBsmcUrbyQvpKLMnV326HiPuvqUv_vvfa8JKBEr8SuUmD</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Automating News Summarization with Sentence Vectors Offset</title><source>IEEE Xplore All Conference Series</source><creator>Steinert, Mauricio ; Granada, Roger ; Aires, Joao Paulo ; Meneguzzi, Felipe</creator><creatorcontrib>Steinert, Mauricio ; Granada, Roger ; Aires, Joao Paulo ; Meneguzzi, Felipe</creatorcontrib><description>Text summaries consist of short versions of texts that convey their key aspects and help readers understand the gist of such texts without reading them in full. Generating such summaries is important for users who must sift through ever-increasing volumes of the content generated on the web. However, generating high-quality summaries is time-consuming for humans and challenging for automated systems, since it involves understanding the semantics of the underlying texts in order to extract key information. In this work, we develop an extractive text summarization method using vector offsets, which we show empirically to be able to summarize texts from an Internet news corpus with an effectiveness competitive with state-of-the-art extractive techniques.</description><identifier>EISSN: 2643-6264</identifier><identifier>EISBN: 9781728142531</identifier><identifier>EISBN: 1728142539</identifier><identifier>DOI: 10.1109/BRACIS.2019.00027</identifier><identifier>CODEN: IEEPAD</identifier><language>eng</language><publisher>IEEE</publisher><subject>automatic text summarization ; Gold ; information retrieval ; Internet ; Mathematical model ; natural language processing ; Neural networks ; Semantics ; Task analysis ; word embedding</subject><ispartof>2019 8th Brazilian Conference on Intelligent Systems (BRACIS), 2019, p.102-107</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/8924017$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,778,782,787,788,27912,54542,54919</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/8924017$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Steinert, Mauricio</creatorcontrib><creatorcontrib>Granada, Roger</creatorcontrib><creatorcontrib>Aires, Joao Paulo</creatorcontrib><creatorcontrib>Meneguzzi, Felipe</creatorcontrib><title>Automating News Summarization with Sentence Vectors Offset</title><title>2019 8th Brazilian Conference on Intelligent Systems (BRACIS)</title><addtitle>BRACIS</addtitle><description>Text summaries consist of short versions of texts that convey their key aspects and help readers understand the gist of such texts without reading them in full. Generating such summaries is important for users who must sift through ever-increasing volumes of the content generated on the web. However, generating high-quality summaries is time-consuming for humans and challenging for automated systems, since it involves understanding the semantics of the underlying texts in order to extract key information. In this work, we develop an extractive text summarization method using vector offsets, which we show empirically to be able to summarize texts from an Internet news corpus with an effectiveness competitive with state-of-the-art extractive techniques.</description><subject>automatic text summarization</subject><subject>Gold</subject><subject>information retrieval</subject><subject>Internet</subject><subject>Mathematical model</subject><subject>natural language processing</subject><subject>Neural networks</subject><subject>Semantics</subject><subject>Task analysis</subject><subject>word embedding</subject><issn>2643-6264</issn><isbn>9781728142531</isbn><isbn>1728142539</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2019</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotjt1KxDAUhKMguKx9APEmL9Cak7T58W4tui4sLlj1dkmaE63YVtosiz69Ab2Z-RiGYQi5BFYAMHN9-7SqN03BGZiCMcbVCcmM0qC4hpJXAk7JgstS5DLpOcnm-SPVBGeirKoFuVkd4tjb2A1v9BGPM20OfW-n7idF40CPXXynDQ4RhxbpK7ZxnGa6C2HGeEHOgv2cMfv3JXm5v3uuH_Ltbr2pV9u8A9AxB-nb0goDAdCp1nJnXBtUKDUyyZjWDhESc-e9cz4RBsmcUrbyQvpKLMnV326HiPuvqUv_vvfa8JKBEr8SuUmD</recordid><startdate>201910</startdate><enddate>201910</enddate><creator>Steinert, Mauricio</creator><creator>Granada, Roger</creator><creator>Aires, Joao Paulo</creator><creator>Meneguzzi, Felipe</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201910</creationdate><title>Automating News Summarization with Sentence Vectors Offset</title><author>Steinert, Mauricio ; Granada, Roger ; Aires, Joao Paulo ; Meneguzzi, Felipe</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i118t-16dc4a391f1eb7ca2b9bcf7f48e060088bee18e02bddbbd8e0ef60b77a5d36d53</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2019</creationdate><topic>automatic text summarization</topic><topic>Gold</topic><topic>information retrieval</topic><topic>Internet</topic><topic>Mathematical model</topic><topic>natural language processing</topic><topic>Neural networks</topic><topic>Semantics</topic><topic>Task analysis</topic><topic>word embedding</topic><toplevel>online_resources</toplevel><creatorcontrib>Steinert, Mauricio</creatorcontrib><creatorcontrib>Granada, Roger</creatorcontrib><creatorcontrib>Aires, Joao Paulo</creatorcontrib><creatorcontrib>Meneguzzi, Felipe</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Steinert, Mauricio</au><au>Granada, Roger</au><au>Aires, Joao Paulo</au><au>Meneguzzi, Felipe</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Automating News Summarization with Sentence Vectors Offset</atitle><btitle>2019 8th Brazilian Conference on Intelligent Systems (BRACIS)</btitle><stitle>BRACIS</stitle><date>2019-10</date><risdate>2019</risdate><spage>102</spage><epage>107</epage><pages>102-107</pages><eissn>2643-6264</eissn><eisbn>9781728142531</eisbn><eisbn>1728142539</eisbn><coden>IEEPAD</coden><abstract>Text summaries consist of short versions of texts that convey their key aspects and help readers understand the gist of such texts without reading them in full. Generating such summaries is important for users who must sift through ever-increasing volumes of the content generated on the web. However, generating high-quality summaries is time-consuming for humans and challenging for automated systems, since it involves understanding the semantics of the underlying texts in order to extract key information. In this work, we develop an extractive text summarization method using vector offsets, which we show empirically to be able to summarize texts from an Internet news corpus with an effectiveness competitive with state-of-the-art extractive techniques.</abstract><pub>IEEE</pub><doi>10.1109/BRACIS.2019.00027</doi><tpages>6</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier EISSN: 2643-6264
ispartof 2019 8th Brazilian Conference on Intelligent Systems (BRACIS), 2019, p.102-107
issn 2643-6264
language eng
recordid cdi_ieee_primary_8924017
source IEEE Xplore All Conference Series
subjects automatic text summarization
Gold
information retrieval
Internet
Mathematical model
natural language processing
Neural networks
Semantics
Task analysis
word embedding
title Automating News Summarization with Sentence Vectors Offset
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-16T00%3A25%3A22IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Automating%20News%20Summarization%20with%20Sentence%20Vectors%20Offset&rft.btitle=2019%208th%20Brazilian%20Conference%20on%20Intelligent%20Systems%20(BRACIS)&rft.au=Steinert,%20Mauricio&rft.date=2019-10&rft.spage=102&rft.epage=107&rft.pages=102-107&rft.eissn=2643-6264&rft.coden=IEEPAD&rft_id=info:doi/10.1109/BRACIS.2019.00027&rft.eisbn=9781728142531&rft.eisbn_list=1728142539&rft_dat=%3Cieee_CHZPO%3E8924017%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i118t-16dc4a391f1eb7ca2b9bcf7f48e060088bee18e02bddbbd8e0ef60b77a5d36d53%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=8924017&rfr_iscdi=true