TIMEX3 and event extraction using recurrent neural networks

Cited 2 time in webofscience Cited 0 time in scopus
  • Hit : 58
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorKim, Zae Myungko
dc.contributor.authorJeong, Young-Seobko
dc.date.accessioned2023-09-22T05:00:26Z-
dc.date.available2023-09-22T05:00:26Z-
dc.date.created2023-09-22-
dc.date.issued2016-01-
dc.identifier.citationInternational Conference on Big Data and Smart Computing, BigComp 2016, pp.450 - 453-
dc.identifier.issn2375-933X-
dc.identifier.urihttp://hdl.handle.net/10203/312868-
dc.description.abstractThis paper investigates the performance of Elman-type and Jordan-type recurrent neural networks (RNN) in extracting temporal information from textual data. The RNN architectures are applied to two tasks of TempEval-2 challenge: (1) extracting the extent of TIMEX3 tags and its TYPE, and (2) extracting the extent of EVENT tags and its CLASS attribute. For the first task, the performances of the RNN models are highly comparable to that of the wining entry for the challenge. For the second task, both models outperform the winning entry, attaining nearly full scores.-
dc.languageEnglish-
dc.publisherInstitute of Electrical and Electronics Engineers Inc.-
dc.titleTIMEX3 and event extraction using recurrent neural networks-
dc.typeConference-
dc.identifier.wosid000381792400082-
dc.identifier.scopusid2-s2.0-84964614218-
dc.type.rimsCONF-
dc.citation.beginningpage450-
dc.citation.endingpage453-
dc.citation.publicationnameInternational Conference on Big Data and Smart Computing, BigComp 2016-
dc.identifier.conferencecountryCC-
dc.identifier.conferencelocationHong Kong-
dc.identifier.doi10.1109/BIGCOMP.2016.7425968-
dc.contributor.localauthorKim, Zae Myung-
dc.contributor.nonIdAuthorJeong, Young-Seob-
Appears in Collection
RIMS Conference Papers
Files in This Item
There are no files associated with this item.
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 2 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0