Conference paper Open Access

Towards Unsupervised Knowledge Extraction

Dorothea Tsatsou; Konstantinos Karageorgos; Anastasios Dimou; Javier Carbo; Jose M. Molina; Petros Daras


Citation Style Language JSON Export

{
  "publisher": "Zenodo", 
  "DOI": "10.5281/zenodo.4686855", 
  "language": "eng", 
  "title": "Towards Unsupervised Knowledge Extraction", 
  "issued": {
    "date-parts": [
      [
        2021, 
        4, 
        9
      ]
    ]
  }, 
  "abstract": "<p>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.</p>", 
  "author": [
    {
      "family": "Dorothea Tsatsou"
    }, 
    {
      "family": "Konstantinos Karageorgos"
    }, 
    {
      "family": "Anastasios Dimou"
    }, 
    {
      "family": "Javier Carbo"
    }, 
    {
      "family": "Jose M. Molina"
    }, 
    {
      "family": "Petros Daras"
    }
  ], 
  "id": "4686855", 
  "note": "CEUR-WS.org/Vol-2846", 
  "type": "paper-conference", 
  "event": "Combining Machine Learning and Knowledge Engineering (AAAI-MAKE 2021)"
}
11
7
views
downloads
All versions This version
Views 1111
Downloads 77
Data volume 7.0 MB7.0 MB
Unique views 1010
Unique downloads 77

Share

Cite as