Articles | Volume 5, issue 2
SOIL, 5, 177–187, 2019
https://doi.org/10.5194/soil-5-177-2019
SOIL, 5, 177–187, 2019
https://doi.org/10.5194/soil-5-177-2019
Original research article
17 Jul 2019
Original research article | 17 Jul 2019

Word embeddings for application in geosciences: development, evaluation, and examples of soil-related concepts

José Padarian and Ignacio Fuentes

Viewed

Total article views: 2,121 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
1,365 685 71 2,121 65 44
  • HTML: 1,365
  • PDF: 685
  • XML: 71
  • Total: 2,121
  • BibTeX: 65
  • EndNote: 44
Views and downloads (calculated since 29 Jan 2019)
Cumulative views and downloads (calculated since 29 Jan 2019)

Viewed (geographical distribution)

Total article views: 1,580 (including HTML, PDF, and XML) Thereof 1,571 with geography defined and 9 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 

Cited

Latest update: 06 Jul 2022
Download
Short summary
A large amount of descriptive information is available in geosciences. Considering the advances in natural language it is possible to rescue this information and transform it into a numerical form (embeddings). We used 280764 full-text scientific articles to train a language model capable of generating such embeddings. Our domain-specific embeddings (GeoVec) outperformed general domain embedding tasks such as analogies, relatedness, and categorisation, and can be used in novel applications.