Analyzing machine-learned representations: A natural language case study

Cognitive science, 2019.

Cited by: 0|Bibtex|Views54|DOI:https://doi.org/10.1111/cogs.12925
WOS
Other Links: arxiv.org|pubmed.ncbi.nlm.nih.gov|academic.microsoft.com

Abstract:

As modern deep networks become more complex, and get closer to human-like capabilities in certain domains, the question arises as to how the representations and decision rules they learn compare to the ones in humans. In this work, we study representations of sentences in one such artificial system for natural language processing. We firs...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments