Go home now Header Background Image
Search
Submission Procedure
share: |
 
Follow us
 
 
 
 
Volume 24 / Issue 10

available in:   PDF (633 kB) PS (771 kB)
 
get:  
Similar Docs BibTeX   Write a comment
  
get:  
Links into Future
 
DOI:   10.3217/jucs-024-10-1378

 

Learning Concept Embeddings from Temporal Data

Francois Meyer (Stellenbosch University,, South Africa)

Brink van der Merwe (Stellenbosch University,, South Africa)

Dirko Coetsee (Praelexis, South Africa)

Abstract: Word embedding techniques can be used to learn vector representations of concepts from temporal datasets. Previous attempts to do this amounted to apply- ing word embedding techniques to event sequences. We propose a concept embedding model that extends existing word embedding techniques to take time into account by explicitly modelling the time between concept occurrences. The model is implemented and evaluated using medical temporal data. It is found that incorporating time into the learning algorithm can improve the quality of the resulting embeddings, as measured by an existing methodological framework for evaluating medical concept embeddings.

Keywords: deep learning, natural language processing, skip-gram, temporal data, word embeddings

Categories: I.2.6, I.2.7, I.5.1