Abstract
Relational Networks (RN) as introduced by Santoro et al. in 2017 have demonstrated strong relational reasoning capabilities with a rather shallow architecture. Its single-layer design, however, only considers pairs of information objects, making it unsuitable for problems requiring reasoning across a higher number of facts. To overcome this limitation, we propose a multi-layer relation network architecture which enables successive refinements of relational information through multiple layers. We show that the increased depth allows for more complex relational reasoning by applying it to the bAbI 20 QA dataset, solving all 20 tasks with joint training and surpassing the state-of-the-art results.
| Original language | English |
|---|---|
| Title of host publication | APPIS '19: Proceedings of the 2nd International Conference on Applications of Intelligent Systems |
| Editors | Nicolai Petkov, Nicola Strisciuglio, Carlos M. Travieso |
| Number of pages | 5 |
| Publisher | ACM |
| Publication date | 07.01.2019 |
| Pages | 1–5 |
| Article number | 10 |
| ISBN (Print) | 978-1-4503-6085-2 |
| DOIs | |
| Publication status | Published - 07.01.2019 |
| Event | 2nd International Conference on Applications of Intelligent Systems - Museo Elder of Science and Technology, Las Palmas de Gran Canaria, Spain Duration: 07.01.2019 → 09.01.2019 Conference number: 149535 |
Research Areas and Centers
- Research Area: Intelligent Systems
- Centers: Center for Artificial Intelligence Luebeck (ZKIL)
DFG Research Classification Scheme
- 4.43-05 Image and Language Processing, Computer Graphics and Visualisation, Human Computer Interaction, Ubiquitous and Wearable Computing
