ruimtehol (Q83038)

From MaRDI portal





Learn Text 'Embeddings' with 'Starspace'
Language Label Description Also known as
default for all languages
No label defined
    English
    ruimtehol
    Learn Text 'Embeddings' with 'Starspace'

      Statements

      0 references
      0.3.1
      6 January 2023
      0 references
      0.1.1
      8 January 2019
      0 references
      0.1.2
      28 January 2019
      0 references
      0.2.1
      31 May 2019
      0 references
      0.2.3
      10 January 2020
      0 references
      0.2.5
      11 October 2020
      0 references
      0.2
      8 May 2019
      0 references
      0.3
      29 November 2020
      0 references
      0.3.2
      22 February 2024
      0 references
      0 references
      22 February 2024
      0 references
      Wraps the 'StarSpace' library <https://github.com/facebookresearch/StarSpace> allowing users to calculate word, sentence, article, document, webpage, link and entity 'embeddings'. By using the 'embeddings', you can perform text based multi-label classification, find similarities between texts and categories, do collaborative-filtering based recommendation as well as content-based recommendation, find out relations between entities, calculate graph 'embeddings' as well as perform semi-supervised learning and multi-task learning on plain text. The techniques are explained in detail in the paper: 'StarSpace: Embed All The Things!' by Wu et al. (2017), available at <arXiv:1709.03856>.
      0 references
      0 references
      0 references
      0 references
      0 references
      0 references

      Identifiers

      0 references