Automatic Text Summarization of COVID-19 Research Articles Using Recurrent Neural Networks and Coreference Resolution
Purpose: Pandemic COVID-19 has created an emergency for the medical community. Researchers require extensive study of scientific literature in order to discover drugs and vaccines. In this situation where every minute is valuable to save the lives of hundreds of people, a quick understanding of scie...
Saved in:
Published in | Frontiers in biomedical technologies Vol. 7; no. 4 |
---|---|
Main Authors | , , |
Format | Journal Article |
Language | English |
Published |
Tehran University of Medical Sciences
06.02.2021
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Purpose: Pandemic COVID-19 has created an emergency for the medical community. Researchers require extensive study of scientific literature in order to discover drugs and vaccines. In this situation where every minute is valuable to save the lives of hundreds of people, a quick understanding of scientific articles will help the medical community. Automatic text summarization makes this possible.
Materials and Methods: In this study, a recurrent neural network-based extractive summarization is proposed. The extractive method identifies the informative parts of the text. Recurrent neural network is very powerful for analyzing sequences such as text. The proposed method has three phases: sentence encoding, sentence ranking, and summary generation. To improve the performance of the summarization system, a coreference resolution procedure is used. Coreference resolution identifies the mentions in the text that refer to the same entity in the real world. This procedure helps to summarization process by discovering the central subject of the text.
Results: The proposed method is evaluated on the COVID-19 research articles extracted from the CORD-19 dataset. The results show that the combination of using recurrent neural network and coreference resolution embedding vectors improves the performance of the summarization system. The Proposed method by achieving the value of ROUGE1-recall 0.53 demonstrates the improvement of summarization performance by using coreference resolution embedding vectors in the RNN-based summarization system.
Conclusion: In this study, coreference information is stored in the form of coreference embedding vectors. Jointly use of recurrent neural network and coreference resolution results in an efficient summarization system. |
---|---|
AbstractList | Purpose: Pandemic COVID-19 has created an emergency for the medical community. Researchers require extensive study of scientific literature in order to discover drugs and vaccines. In this situation where every minute is valuable to save the lives of hundreds of people, a quick understanding of scientific articles will help the medical community. Automatic text summarization makes this possible. Materials and Methods: In this study, a recurrent neural network-based extractive summarization is proposed. The extractive method identifies the informative parts of the text. Recurrent neural network is very powerful for analyzing sequences such as text. The proposed method has three phases: sentence encoding, sentence ranking, and summary generation. To improve the performance of the summarization system, a coreference resolution procedure is used. Coreference resolution identifies the mentions in the text that refer to the same entity in the real world. This procedure helps to summarization process by discovering the central subject of the text. Results: The proposed method is evaluated on the COVID-19 research articles extracted from the CORD-19 dataset. The results show that the combination of using recurrent neural network and coreference resolution embedding vectors improves the performance of the summarization system. The Proposed method by achieving the value of ROUGE1-recall 0.53 demonstrates the improvement of summarization performance by using coreference resolution embedding vectors in the RNN-based summarization system. Conclusion: In this study, coreference information is stored in the form of coreference embedding vectors. Jointly use of recurrent neural network and coreference resolution results in an efficient summarization system. Purpose: Pandemic COVID-19 has created an emergency for the medical community. Researchers require extensive study of scientific literature in order to discover drugs and vaccines. In this situation where every minute is valuable to save the lives of hundreds of people, a quick understanding of scientific articles will help the medical community. Automatic text summarization makes this possible. Materials and Methods: In this study, a recurrent neural network-based extractive summarization is proposed. The extractive method identifies the informative parts of the text. Recurrent neural network is very powerful for analyzing sequences such as text. The proposed method has three phases: sentence encoding, sentence ranking, and summary generation. To improve the performance of the summarization system, a coreference resolution procedure is used. Coreference resolution identifies the mentions in the text that refer to the same entity in the real world. This procedure helps to summarization process by discovering the central subject of the text. Results: The proposed method is evaluated on the COVID-19 research articles extracted from the CORD-19 dataset. The results show that the combination of using recurrent neural network and coreference resolution embedding vectors improves the performance of the summarization system. The Proposed method by achieving the value of ROUGE1-recall 0.53 demonstrates the improvement of summarization performance by using coreference resolution embedding vectors in the RNN-based summarization system. Conclusion: In this study, coreference information is stored in the form of coreference embedding vectors. Jointly use of recurrent neural network and coreference resolution results in an efficient summarization system. |
Author | Ebrahimpour-Komleh, Hossein Bagheri, Ayoub Afsharizadeh, Mahsa |
Author_xml | – sequence: 1 givenname: Mahsa surname: Afsharizadeh fullname: Afsharizadeh, Mahsa – sequence: 2 givenname: Hossein surname: Ebrahimpour-Komleh fullname: Ebrahimpour-Komleh, Hossein – sequence: 3 givenname: Ayoub surname: Bagheri fullname: Bagheri, Ayoub |
BookMark | eNpNkdtOAjEQhhuDiYjcet0XWJwedtu9JHgiIZIoeNt0S4uLsDXtrqent4AxXs3kn8mX_PnOUa_xjUXoksCIyBzolava0buo-ShnlJygPmU8z3LJRO_ffoaGMW4AgEjKSkn7qBt3rd_ptjZ4YT9b_NTtdjrU3ynxDfYOT-bP0-uMlPjRRquDecHjkL63NuJlrJt1yk0Xgm1a_GC7oLdptB8-vEasmxWe-GCdTWdj9wS_7fbgC3Tq9Dba4e8coOXtzWJyn83md9PJeJYZSqHNSk5ELqgBA5AzwRlAUelCSsm4LQoH3OWwsqUBW1alFgQMc6V2DqTkhEs2QNMjd-X1Rr2FOnX7Ul7X6hD4sFb62EYZykvjVowKIrgQtKo4YUJUlFhGBCsSa3RkmeBjTK3-eATUwYFKDtTegdo7YD_KcHu2 |
CitedBy_id | crossref_primary_10_52547_jist_16245_10_37_68 |
ContentType | Journal Article |
DBID | AAYXX CITATION DOA |
DOI | 10.18502/fbt.v7i4.5321 |
DatabaseName | CrossRef Directory of Open Access Journals |
DatabaseTitle | CrossRef |
DatabaseTitleList | CrossRef |
Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website |
DeliveryMethod | fulltext_linktorsrc |
EISSN | 2345-5837 |
ExternalDocumentID | oai_doaj_org_article_c249cfd327174772bb41377b21e31736 10_18502_fbt_v7i4_5321 |
GroupedDBID | AAYXX ALMA_UNASSIGNED_HOLDINGS ARCSS CITATION GROUPED_DOAJ M~E OK1 |
ID | FETCH-LOGICAL-c220t-9417572c0c0053743006ba688834e66f04f50de9c0e9b9a710c3f9aff08841483 |
IEDL.DBID | DOA |
ISSN | 2345-5837 |
IngestDate | Thu Jul 04 21:06:40 EDT 2024 Fri Aug 23 00:57:23 EDT 2024 |
IsDoiOpenAccess | true |
IsOpenAccess | true |
IsPeerReviewed | true |
IsScholarly | true |
Issue | 4 |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c220t-9417572c0c0053743006ba688834e66f04f50de9c0e9b9a710c3f9aff08841483 |
OpenAccessLink | https://doaj.org/article/c249cfd327174772bb41377b21e31736 |
ParticipantIDs | doaj_primary_oai_doaj_org_article_c249cfd327174772bb41377b21e31736 crossref_primary_10_18502_fbt_v7i4_5321 |
PublicationCentury | 2000 |
PublicationDate | 2021-02-06 |
PublicationDateYYYYMMDD | 2021-02-06 |
PublicationDate_xml | – month: 02 year: 2021 text: 2021-02-06 day: 06 |
PublicationDecade | 2020 |
PublicationTitle | Frontiers in biomedical technologies |
PublicationYear | 2021 |
Publisher | Tehran University of Medical Sciences |
Publisher_xml | – name: Tehran University of Medical Sciences |
SSID | ssj0001823982 |
Score | 2.212878 |
Snippet | Purpose: Pandemic COVID-19 has created an emergency for the medical community. Researchers require extensive study of scientific literature in order to... |
SourceID | doaj crossref |
SourceType | Open Website Aggregation Database |
SubjectTerms | Coreference Resolution COVID-19 Extractive Summarization Gated Recurrent Unit Long Short Term Memory Recurrent Neural Network |
Title | Automatic Text Summarization of COVID-19 Research Articles Using Recurrent Neural Networks and Coreference Resolution |
URI | https://doaj.org/article/c249cfd327174772bb41377b21e31736 |
Volume | 7 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV07T8MwELZQJxYEAkR5yQMSU6hfSZuxFKqCRBloUbfIT4klRTT9_72zUygTC6sVOdF39t198fk7Qm60NBBH-i7DI55MBZ5nesDxwNXZYJ0VRZRSepkWk7l6XuSLnVZfWBOW5IETcD0L_MAGJwXwDgWpoDEKRfKM4B5Cn0xi2zzfIVPx78oAde1Eq9I4yJnoBQM7vv-h7nIp-K8otCPWH6PK-JActOkgHabPOCJ7vj4m6-G6WUYpVToD30nf4gWz9sIkXQY6en1_esh4Sbd1c9sJVjSWAMC4TbpLFMU34AXTVO29orp2dPTTXARnaBffCZmPH2ejSda2R8isEKzJSgWhvy8ss1GURUnYQEYXQGml8kURmAo5c760zJem1JBKWBlKHQI4FgUsSJ6STr2s_RmhtigFUGymXYB8hCktuAHQgwb3o4WzXXK7hav6TCoYFbIHBLYCYCsEtkJgu-Qe0fx-CtWr4wDYtGptWv1l0_P_mOSC7AusP8EK6-KSdJqvtb-CBKIx13GtbADYKsKP |
link.rule.ids | 315,786,790,870,2115,27957,27958 |
linkProvider | Directory of Open Access Journals |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Automatic+Text+Summarization+of+COVID-19+Research+Articles+Using+Recurrent+Neural+Networks+and+Coreference+Resolution&rft.jtitle=Frontiers+in+biomedical+technologies&rft.au=Mahsa+Afsharizadeh&rft.au=Hossein+Ebrahimpour-Komleh&rft.au=Ayoub+Bagheri&rft.date=2021-02-06&rft.pub=Tehran+University+of+Medical+Sciences&rft.eissn=2345-5837&rft.volume=7&rft.issue=4&rft_id=info:doi/10.18502%2Ffbt.v7i4.5321&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_c249cfd327174772bb41377b21e31736 |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2345-5837&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2345-5837&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2345-5837&client=summon |