A framework for computing answers to broad and complex questions
Today, information is more easily available worldwide. However, because it is conveyed through automated systems, access to it is restricted by these systems’ ability to understand language. Current systems are unable to answer complex questions in broad domains. This is because they can’t break questions down into parts and find the relevant information in different sources. The EU-funded DELPHI project aims to show that computers can answer wide-ranging and intricate questions that require reasoning over multiple modalities. To this end, it proposes a framework where complex questions are symbolically decomposed into subquestions. Each is answered with a neural network, and the final answer is computed from all gathered information. This work has the potential to change future human-machine interaction.
Fields of science
Funding SchemeERC-STG - Starting Grant
69978 Tel Aviv
See on map