Cover Image
QR Code

Research for Practice: Knowledge Base Construction in the Machine-Learning Era.

The article reports on the construction of knowledge bases through the use of deep learning. It presents summaries of three papers on several facets of knowledge base construction: the need for joint learning to prevent error cascades, the weak supervision of training data, and the representation of...

Full description

Published in:Communications of the ACM Vol. 61; no. 11; pp. 95 - 98
Main Authors: RATNER, ALEX, RÉ, CHRIS
Format: Article
Published: Association for Computing Machinery Nov2018
Subjects:
Knowledge base
Deep learning
Data
Errors
Computer programming
Online Access:View this record in EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=132883492&site=ehost-live
header:
  @attributes:
    shortDbName: hlh
    uiTerm: 132883492
    longDbName: Humanities International Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    jinfo:
      jid:
        00010782
        ACM
      jtl: Communications of the ACM
      issn: 00010782
      maglogo: N
    pubinfo:
      dt: Nov2018
      vid: 61
      iid: 11
      pid: 68
      pub: Association for Computing Machinery
    artinfo:
      ui:
        132883492
        10.1145/3233243
      ppf: 95
      ppct: 3
      formats:
      tig:
        atl: Research for Practice: Knowledge Base Construction in the Machine-Learning Era.
      aug:
        au:
          RATNER, ALEX
          RÉ, CHRIS
        affil:
          Ph.D. candidate in computer science at Stanford University
          Associate professor of computer science at Stanford University
      su:
        Knowledge base
        Deep learning
        Data
        Errors
        Computer programming
      sug:
        subj:
          Knowledge base
          Deep learning
          Data
          Errors
          Computer programming
      ab: The article reports on the construction of knowledge bases through the use of deep learning. It presents summaries of three papers on several facets of knowledge base construction: the need for joint learning to prevent error cascades, the weak supervision of training data, and the representation of the data both as it is input and output.
      pubtype: Periodical
      doctype: Article
      src: R
    language: English
    refInfo:
    copyright:
      @attributes:
        flag: Y
      dt:
        @attributes:
          year: 2018
    holdings:
      @attributes:
        islocal: N