Conference paper Open Access
Towards Unsupervised Knowledge Extraction
Dorothea Tsatsou;
Konstantinos Karageorgos;
Anastasios Dimou;
Javier Carbo;
Jose M. Molina;
Petros Daras
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.
| Name | Size | |
|---|---|---|
|
paper21.pdf
md5:1dee2bbcf5ea7396bc9005da61c059e7 |
1.0 MB | Download |
| All versions | This version | |
|---|---|---|
| Views | 73 | 73 |
| Downloads | 42 | 42 |
| Data volume | 42.1 MB | 42.1 MB |
| Unique views | 68 | 68 |
| Unique downloads | 41 | 41 |
- Publication date:
- April 9, 2021
- DOI:
-
- Keyword(s):
- knowledge extraction unsupervised learning spectral analysis knowledge representation symbolic AI sub-symbolic AI neural-symbolic integration neurosymbolic integration
- Grants:
-
European Commission:
- ANITA - Advanced tools for fighting oNline Illegal TrAfficking (787061)
- Meeting:
- Combining Machine Learning and Knowledge Engineering (AAAI-MAKE 2021), March 22-24, 2021
- Alternate identifiers:
- Communities:
- License (for files):
- Creative Commons Attribution 4.0 International