Skip to main content
Go to the home page of the European Commission (opens in new window)
English en
CORDIS - EU research results
CORDIS

Hyperquest – semantic hypergraphs for augmented information retrieval

Project description

A novel way to extract meaning from large volumes of text

Companies face significant challenges extracting meaning from the voluminous documents they encounter daily. Tools exist to support these efforts, but they are lacking in rigour and specificity. The ERC-funded HyperQuest project is turning unstructured text into structured knowledge. It extracts information from large text collections using linguistic patterns that are easy to define, yet expressive enough to capture the richness of natural language. The extracted knowledge can then be explored through semantic graphs, stored in relational databases, or provided to large language models as structured context for downstream extraction and reasoning.

Objective

HyperQuest aims at creating a tool for knowledge extraction from text documents via iterative contextual learning, for use by medium-sized and large companies where these needs are recurrent (automatic document analysis and editing, information retrieval from internal databases, etc.). It aims at overcoming technological barriers by creating intuitive interfaces to help users co-construct complex knowledge extraction and transformation tasks simply and with very few examples, at a level of specificity and rigor that current tools do not allow. HyperQuest is based on our innovation, semantic hypergraphs, at the confluence of symbolic and connectionist (machine/deep learning) Artificial Intelligence.

Keywords

Programme(s)

Topic(s)

Funding Scheme

HORIZON-ERC-POC - HORIZON ERC Proof of Concept Grants

See all projects funded under this funding scheme

Call for proposal

(opens in new window) ERC-2025-POC

See all projects funded under this call

Host institution

CENTRE NATIONAL DE LA RECHERCHE SCIENTIFIQUE CNRS
Net EU contribution
€ 145 000,00
Address
RUE MICHEL ANGE 3
75794 Paris
France
Region
Ile-de-France Ile-de-France Paris
Activity type
Research Organisations
Links
Total cost
No data

Beneficiaries (2)