View in EDS PDF Full Text

Word Embeddings: Reliability & Semantic Change

Saved in:
Bibliographic Details
Title: Word Embeddings: Reliability & Semantic Change
Description: 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.
Authors: Johannes Hellrich
Resource Type: eBook.
Subjects: Artificial intelligence, Natural language processing (Computer science)
Categories: COMPUTERS / Artificial Intelligence / General
Database: eBook Collection (EBSCOhost)
FullText Links:
  – Type: ebook-pdf
Text:
  Availability: 0
Header DbId: nlebk
DbLabel: eBook Collection (EBSCOhost)
An: 2253899
RelevancyScore: 1090
AccessLevel: 6
PubType: eBook
PubTypeId: ebook
PreciseRelevancyScore: 1090.09973144531
IllustrationInfo
ImageInfo – Size: thumb
  Target: https://rps2images.ebscohost.com/rpsweb/othumb?id=NL$2253899$PDF&s=r
– Size: medium
  Target: https://rps2images.ebscohost.com/rpsweb/othumb?id=NL$2253899$PDF&s=d
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Word Embeddings: Reliability & Semantic Change
– Name: Abstract
  Label: Description
  Group: Ab
  Data: 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.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Johannes+Hellrich%22">Johannes Hellrich</searchLink>
– Name: TypePub
  Label: Resource Type
  Group: TypPub
  Data: eBook.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Artificial+intelligence%22">Artificial intelligence</searchLink><br /><searchLink fieldCode="DE" term="%22Natural+language+processing+%28Computer+science%29%22">Natural language processing (Computer science)</searchLink>
– Name: SubjectBISAC
  Label: Categories
  Group: Su
  Data: <searchLink fieldCode="ZK" term="%22COMPUTERS+%2F+Artificial+Intelligence+%2F+General%22">COMPUTERS / Artificial Intelligence / General</searchLink>
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=nlebk&AN=2253899
RecordInfo BibRecord:
  BibEntity:
    Classifications:
      – Code: 006.35
        Scheme: ddc
        Type: prePub
    Languages:
      – Code: eng
        Text: English
    Subjects:
      – SubjectFull: Artificial intelligence
        Type: general
      – SubjectFull: Natural language processing (Computer science)
        Type: general
    Titles:
      – TitleFull: Word Embeddings: Reliability & Semantic Change
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Johannes Hellrich
      – PersonEntity:
          Name:
            NameFull: Johannes Hellrich
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2019
            – D: 24
              M: 09
              Type: profile
              Y: 2019
          Identifiers:
            – Type: isbn-print
              Value: 9781614999942
            – Type: isbn-electronic
              Value: 9781614999959
          Numbering:
            – Type: volume
              Value: 00347
          Titles:
            – TitleFull: Word Embeddings: Reliability & Semantic Change
              Type: main
ResultId 1