Published April 9, 2021 | Version v1
Conference paper Open

Towards Unsupervised Knowledge Extraction

  • 1. Centre for Research and Technology Hellas (CERTH), University Carlos III of Madrid
  • 2. Centre for Research and Technology Hellas (CERTH)
  • 3. University Carlos III of Madrid

Description

Integration of symbolic and sub-symbolic approaches is rapidly emerging as an Artificial Intelligence (AI) paradigm. This paper presents a proof-of-concept approach towards an unsupervised learning method, based on Restricted Boltzmann Machines (RBMs), for extracting semantic associations among prominent entities within data. Validation of the approach is performed in two datasets that connect language and vision, namely Visual Genome and GQA. A methodology to formally structure the extracted knowledge for subsequent use through reasoning engines is also offered.

Notes

CEUR-WS.org/Vol-2846

Files

paper21.pdf

Files (1.0 MB)

Name Size Download all
md5:1dee2bbcf5ea7396bc9005da61c059e7
1.0 MB Preview Download

Additional details

Identifiers

Funding

ANITA – Advanced tools for fighting oNline Illegal TrAfficking 787061
European Commission