MARC 닫기

• LDR

  02601cam c2200433Ii 4500

• 001

  000000529851

• 005

  20200210173846

• 006

  m d

• 007

  cr cnu|||unuuu

• 008

  190920s2019 gw ob 000 0 eng d

• 020

  ▼a  9781614999959
  ▼q  (electronic bk.)

• 020

  ▼a  1614999953
  ▼q  (electronic bk.)

• 020

  ▼z  9781614999942

• 035

  ▼a  2253899
  ▼b  (N$T)

• 035

  ▼a  (OCoLC)1120124334

• 040

  ▼a  N$T
  ▼b  eng
  ▼e  rda
  ▼e  pn
  ▼c  N$T
  ▼d  N$T
  ▼d  248023

• 049

  ▼a  MAIN

• 050

  ▼a  QA76.9.N38

• 082

  ▼a  006.35
  ▼2  23

• 100

  ▼a  Hellrich, Johannes,
  ▼e  author.

• 245

  ▼a  Word embeddings:
  ▼b  reliability & semantic change /:
  ▼c  Johannes Hellrich.
  ▼h  [electronic resource].

• 260

  ▼a  Berlin:
  ▼b  Akademische Verlagsgesellschaft AKA GmbH ;
  ▼a  Amsterdam, the Netherlands:
  ▼b  IOS Press,
  ▼c  [2019].

• 300

  ▼a  1 online resource.

• 336

  ▼a  text
  ▼b  txt
  ▼2  rdacontent

• 337

  ▼a  computer
  ▼b  c
  ▼2  rdamedia

• 338

  ▼a  online resource
  ▼b  cr
  ▼2  rdacarrier

• 490

  ▼a  Dissertations in artificial intelligence;
  ▼v  DISKI 347

• 504

  ▼a  Includes bibliographical references.

• 520

  ▼a  Word embeddings are a form of distributional semantics increasingly popular for investigating lexical semantic change. However, typical training algorithms are probabilistic, limiting their reliability and the reproducibility of studies. Johannes Hellrich investigated this problem both empirically and theoretically and found some variants of SVD-based algorithms to be unaffected. Furthermore, he created the JeSemE website to make word embedding based diachronic research more accessible. It provides information on changes in word denotation and emotional connotation in five diachronic corpora. Finally, the author conducted two case studies on the applicability of these methods by investigating the historical understanding of electricity as well as words connected to Romanticism. They showed the high potential of distributional semantics for further applications in the digital humanities.

• 588

  ▼a  On-line resource; title from PDF title page (EBSCO, viewed September 23, 2019)

• 590

  ▼a  Master record variable field(s) change: 050, 082, 650

• 650

  ▼a  Natural language processing (Computer science)

• 650

  ▼a  Artificial intelligence.

• 655

  ▼a  Electronic books.

• 830

  ▼a  Frontiers in artificial intelligence and applications.
  ▼p  Dissertations in artificial intelligence;
  ▼v  DISKI 347.

• 852

  ▼a  NA000000
  ▼b  00000140

• 856

  ▼3  EBSCOhost
  ▼u  http://search.ebscohost.com/login.aspx?direct=true&scope=site&db=nlebk&db=nlabk&AN=2253899

• 938

  ▼a  EBSCOhost
  ▼b  EBSC
  ▼n  2253899

• 994

  ▼a  92
  ▼b  N$T