Skip to main content
European Commission logo
English English
CORDIS - EU research results
CORDIS
CORDIS Web 30th anniversary CORDIS Web 30th anniversary

Computing Answers to Complex Questions in Broad Domains

Project description

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.

Objective

The explosion of information around us has democratized knowledge and transformed its availability for
people around the world. Still, since information is mediated through automated systems, access is bounded
by their ability to understand language.
Consider an economist asking “What fraction of the top-5 growing countries last year raised their co2 emission?”.
While the required information is available, answering such complex questions automatically is
not possible. Current question answering systems can answer simple questions in broad domains, or complex
questions in narrow domains. However, broad and complex questions are beyond the reach of state-of-the-art.
This is because systems are unable to decompose questions into their parts, and find the relevant information
in multiple sources. Further, as answering such questions is hard for people, collecting large datasets to train
such models is prohibitive.
In this proposal I ask: Can computers answer broad and complex questions that require reasoning over
multiple modalities? I argue that by synthesizing the advantages of symbolic and distributed representations
the answer will be “yes”. My thesis is that symbolic representations are suitable for meaning composition, as
they provide interpretability, coverage, and modularity. Complementarily, distributed representations (learned
by neural nets) excel at capturing the fuzziness of language. I propose a framework where complex questions
are symbolically decomposed into sub-questions, each is answered with a neural network, and the final answer
is computed from all gathered information.
This research tackles foundational questions in language understanding. What is the right representation
for reasoning in language? Can models learn to perform complex actions in the face of paucity of data?
Moreover, my research, if successful, will transform how we interact with machines, and define a role for
them as research assistants in science, education, and our daily life.

Host institution

TEL AVIV UNIVERSITY
Net EU contribution
€ 1 499 375,00
Total cost
€ 1 499 375,00

Beneficiaries (1)