Frame-based Neural Network for Machine Reading Comprehension
Machine Reading Comprehension (MRC) is one of the most challenging tasks in Natural Language Understanding (NLU). In particular, MRC systems typically answer a question by only utilizing the information contained in a given piece of text passage itself, while human beings can easily understand the m...
Gespeichert in:
Veröffentlicht in: | Knowledge-based systems 2021-05, Vol.219, p.106889, Article 106889 |
---|---|
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 | 106889 |
container_title | Knowledge-based systems |
container_volume | 219 |
creator | Guo, Shaoru Guan, Yong Tan, Hongye Li, Ru Li, Xiaoli |
description | Machine Reading Comprehension (MRC) is one of the most challenging tasks in Natural Language Understanding (NLU). In particular, MRC systems typically answer a question by only utilizing the information contained in a given piece of text passage itself, while human beings can easily understand the meanings of the passage based on their background knowledge. To bridge the gap, we propose a novel Frame-based Neural Network for Machine Reading Comprehension(FNN-MRC) method, which employs Frame semantic knowledge to facilitate question answering. Specifically, different from existing Frame based methods that only model lexical units (LUs), our FNN-MRC has a Frame representation model, which utilizes both LUs in Frame and Frame-to-Frame (F-to-F) relations, designed to model Frames and sentences (in passage) together with attention schema. In addition, FNN-MRC has a Frame-based Sentence Representation (FSR) model, which is able to integrate multiple-Frame semantic information to obtain much better sentence representation. As such, FNN-MRC explicitly leverages the above Frame knowledge to assist its semantic understanding and representation. Extensive experiments demonstrate that our FNN-MRC method is able to achieve better results than existing state-of-the-art techniques across multiple datasets. |
doi_str_mv | 10.1016/j.knosys.2021.106889 |
format | Article |
fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2610114888</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0950705121001520</els_id><sourcerecordid>2610114888</sourcerecordid><originalsourceid>FETCH-LOGICAL-c334t-4266755221581e815e7a28c991bc6e47b48689e4bdc90268e1d920d1c3106d993</originalsourceid><addsrcrecordid>eNp9kEFLAzEUhIMoWKv_wMOC561JNptNQAQpVoWqIHoO2eTVZtsmNdkq_femrGdPA483M8yH0CXBE4IJv-4mKx_SPk0opiSfuBDyCI2IaGjZMCyP0QjLGpcNrskpOkupwxhTSsQI3cyi3kDZ6gS2eIFd1Oss_U-Iq2IRYvGszdJ5KN5AW-c_i2nYbCMswScX_Dk6Weh1gos_HaOP2f379LGcvz48Te_mpakq1peMct7UdS6sBQFBamg0FUZK0hoOrGmZ4EICa62RmHIBxEqKLTFVnmKlrMboasjdxvC1g9SrLuyiz5WK8kyAMCFE_mLDl4khpQgLtY1uo-NeEawOnFSnBk7qwEkNnLLtdrBBXvDtIKpkHHgD1kUwvbLB_R_wCy2pcN0</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2610114888</pqid></control><display><type>article</type><title>Frame-based Neural Network for Machine Reading Comprehension</title><source>ScienceDirect Freedom Collection (Elsevier)</source><creator>Guo, Shaoru ; Guan, Yong ; Tan, Hongye ; Li, Ru ; Li, Xiaoli</creator><creatorcontrib>Guo, Shaoru ; Guan, Yong ; Tan, Hongye ; Li, Ru ; Li, Xiaoli</creatorcontrib><description>Machine Reading Comprehension (MRC) is one of the most challenging tasks in Natural Language Understanding (NLU). In particular, MRC systems typically answer a question by only utilizing the information contained in a given piece of text passage itself, while human beings can easily understand the meanings of the passage based on their background knowledge. To bridge the gap, we propose a novel Frame-based Neural Network for Machine Reading Comprehension(FNN-MRC) method, which employs Frame semantic knowledge to facilitate question answering. Specifically, different from existing Frame based methods that only model lexical units (LUs), our FNN-MRC has a Frame representation model, which utilizes both LUs in Frame and Frame-to-Frame (F-to-F) relations, designed to model Frames and sentences (in passage) together with attention schema. In addition, FNN-MRC has a Frame-based Sentence Representation (FSR) model, which is able to integrate multiple-Frame semantic information to obtain much better sentence representation. As such, FNN-MRC explicitly leverages the above Frame knowledge to assist its semantic understanding and representation. Extensive experiments demonstrate that our FNN-MRC method is able to achieve better results than existing state-of-the-art techniques across multiple datasets.</description><identifier>ISSN: 0950-7051</identifier><identifier>EISSN: 1872-7409</identifier><identifier>DOI: 10.1016/j.knosys.2021.106889</identifier><language>eng</language><publisher>Amsterdam: Elsevier B.V</publisher><subject>Frame representation ; Frame semantics ; Machine reading comprehension ; Multiple-Frame semantic integration ; Neural networks ; Questions ; Reading comprehension ; Representations ; Semantics ; Sentences</subject><ispartof>Knowledge-based systems, 2021-05, Vol.219, p.106889, Article 106889</ispartof><rights>2021 Elsevier B.V.</rights><rights>Copyright Elsevier Science Ltd. May 11, 2021</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c334t-4266755221581e815e7a28c991bc6e47b48689e4bdc90268e1d920d1c3106d993</citedby><cites>FETCH-LOGICAL-c334t-4266755221581e815e7a28c991bc6e47b48689e4bdc90268e1d920d1c3106d993</cites><orcidid>0000-0003-4130-3924</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://dx.doi.org/10.1016/j.knosys.2021.106889$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>314,780,784,3550,27924,27925,45995</link.rule.ids></links><search><creatorcontrib>Guo, Shaoru</creatorcontrib><creatorcontrib>Guan, Yong</creatorcontrib><creatorcontrib>Tan, Hongye</creatorcontrib><creatorcontrib>Li, Ru</creatorcontrib><creatorcontrib>Li, Xiaoli</creatorcontrib><title>Frame-based Neural Network for Machine Reading Comprehension</title><title>Knowledge-based systems</title><description>Machine Reading Comprehension (MRC) is one of the most challenging tasks in Natural Language Understanding (NLU). In particular, MRC systems typically answer a question by only utilizing the information contained in a given piece of text passage itself, while human beings can easily understand the meanings of the passage based on their background knowledge. To bridge the gap, we propose a novel Frame-based Neural Network for Machine Reading Comprehension(FNN-MRC) method, which employs Frame semantic knowledge to facilitate question answering. Specifically, different from existing Frame based methods that only model lexical units (LUs), our FNN-MRC has a Frame representation model, which utilizes both LUs in Frame and Frame-to-Frame (F-to-F) relations, designed to model Frames and sentences (in passage) together with attention schema. In addition, FNN-MRC has a Frame-based Sentence Representation (FSR) model, which is able to integrate multiple-Frame semantic information to obtain much better sentence representation. As such, FNN-MRC explicitly leverages the above Frame knowledge to assist its semantic understanding and representation. Extensive experiments demonstrate that our FNN-MRC method is able to achieve better results than existing state-of-the-art techniques across multiple datasets.</description><subject>Frame representation</subject><subject>Frame semantics</subject><subject>Machine reading comprehension</subject><subject>Multiple-Frame semantic integration</subject><subject>Neural networks</subject><subject>Questions</subject><subject>Reading comprehension</subject><subject>Representations</subject><subject>Semantics</subject><subject>Sentences</subject><issn>0950-7051</issn><issn>1872-7409</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><recordid>eNp9kEFLAzEUhIMoWKv_wMOC561JNptNQAQpVoWqIHoO2eTVZtsmNdkq_femrGdPA483M8yH0CXBE4IJv-4mKx_SPk0opiSfuBDyCI2IaGjZMCyP0QjLGpcNrskpOkupwxhTSsQI3cyi3kDZ6gS2eIFd1Oss_U-Iq2IRYvGszdJ5KN5AW-c_i2nYbCMswScX_Dk6Weh1gos_HaOP2f379LGcvz48Te_mpakq1peMct7UdS6sBQFBamg0FUZK0hoOrGmZ4EICa62RmHIBxEqKLTFVnmKlrMboasjdxvC1g9SrLuyiz5WK8kyAMCFE_mLDl4khpQgLtY1uo-NeEawOnFSnBk7qwEkNnLLtdrBBXvDtIKpkHHgD1kUwvbLB_R_wCy2pcN0</recordid><startdate>20210511</startdate><enddate>20210511</enddate><creator>Guo, Shaoru</creator><creator>Guan, Yong</creator><creator>Tan, Hongye</creator><creator>Li, Ru</creator><creator>Li, Xiaoli</creator><general>Elsevier B.V</general><general>Elsevier Science Ltd</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>8FD</scope><scope>E3H</scope><scope>F2A</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><orcidid>https://orcid.org/0000-0003-4130-3924</orcidid></search><sort><creationdate>20210511</creationdate><title>Frame-based Neural Network for Machine Reading Comprehension</title><author>Guo, Shaoru ; Guan, Yong ; Tan, Hongye ; Li, Ru ; Li, Xiaoli</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c334t-4266755221581e815e7a28c991bc6e47b48689e4bdc90268e1d920d1c3106d993</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Frame representation</topic><topic>Frame semantics</topic><topic>Machine reading comprehension</topic><topic>Multiple-Frame semantic integration</topic><topic>Neural networks</topic><topic>Questions</topic><topic>Reading comprehension</topic><topic>Representations</topic><topic>Semantics</topic><topic>Sentences</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Guo, Shaoru</creatorcontrib><creatorcontrib>Guan, Yong</creatorcontrib><creatorcontrib>Tan, Hongye</creatorcontrib><creatorcontrib>Li, Ru</creatorcontrib><creatorcontrib>Li, Xiaoli</creatorcontrib><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Technology Research Database</collection><collection>Library & Information Sciences Abstracts (LISA)</collection><collection>Library & Information Science Abstracts (LISA)</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>Knowledge-based systems</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Guo, Shaoru</au><au>Guan, Yong</au><au>Tan, Hongye</au><au>Li, Ru</au><au>Li, Xiaoli</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Frame-based Neural Network for Machine Reading Comprehension</atitle><jtitle>Knowledge-based systems</jtitle><date>2021-05-11</date><risdate>2021</risdate><volume>219</volume><spage>106889</spage><pages>106889-</pages><artnum>106889</artnum><issn>0950-7051</issn><eissn>1872-7409</eissn><abstract>Machine Reading Comprehension (MRC) is one of the most challenging tasks in Natural Language Understanding (NLU). In particular, MRC systems typically answer a question by only utilizing the information contained in a given piece of text passage itself, while human beings can easily understand the meanings of the passage based on their background knowledge. To bridge the gap, we propose a novel Frame-based Neural Network for Machine Reading Comprehension(FNN-MRC) method, which employs Frame semantic knowledge to facilitate question answering. Specifically, different from existing Frame based methods that only model lexical units (LUs), our FNN-MRC has a Frame representation model, which utilizes both LUs in Frame and Frame-to-Frame (F-to-F) relations, designed to model Frames and sentences (in passage) together with attention schema. In addition, FNN-MRC has a Frame-based Sentence Representation (FSR) model, which is able to integrate multiple-Frame semantic information to obtain much better sentence representation. As such, FNN-MRC explicitly leverages the above Frame knowledge to assist its semantic understanding and representation. Extensive experiments demonstrate that our FNN-MRC method is able to achieve better results than existing state-of-the-art techniques across multiple datasets.</abstract><cop>Amsterdam</cop><pub>Elsevier B.V</pub><doi>10.1016/j.knosys.2021.106889</doi><orcidid>https://orcid.org/0000-0003-4130-3924</orcidid></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0950-7051 |
ispartof | Knowledge-based systems, 2021-05, Vol.219, p.106889, Article 106889 |
issn | 0950-7051 1872-7409 |
language | eng |
recordid | cdi_proquest_journals_2610114888 |
source | ScienceDirect Freedom Collection (Elsevier) |
subjects | Frame representation Frame semantics Machine reading comprehension Multiple-Frame semantic integration Neural networks Questions Reading comprehension Representations Semantics Sentences |
title | Frame-based Neural Network for Machine Reading Comprehension |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T05%3A28%3A51IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Frame-based%20Neural%20Network%20for%20Machine%20Reading%20Comprehension&rft.jtitle=Knowledge-based%20systems&rft.au=Guo,%20Shaoru&rft.date=2021-05-11&rft.volume=219&rft.spage=106889&rft.pages=106889-&rft.artnum=106889&rft.issn=0950-7051&rft.eissn=1872-7409&rft_id=info:doi/10.1016/j.knosys.2021.106889&rft_dat=%3Cproquest_cross%3E2610114888%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2610114888&rft_id=info:pmid/&rft_els_id=S0950705121001520&rfr_iscdi=true |