Initiative #63
Factoid Finder Tool
Listed in the registry Pilot Original language : English
About the initiative
Description of the initiative
The Factoid Finder extracts text from machine-readable PDFs to create searchable content libraries. Small Language Models are used to implement semantic search techniques, allowing users to search the library for relevant passages within the PDFs. Small Language Model and Text Embedder: MS Marco Distilbert Dot-v5 Cross-encoder: MS Marco MiniLM-L6-v2
AI family
Bucket rationale
Synthesizes knowledge and makes sense of document stores via semantics—generative/knowledge management.
Lifecycle
-
Ideation
Stage status : Completed
May 29, 2025
-
Assessment
Stage status : Completed
-
Approved
Stage status : Completed
-
Development
Stage status : Completed
-
Pilot
Stage status : In progress
-
Production
Stage status : Upcoming
-
Archived
Stage status : Upcoming
Schedule for this initiative
- Completed
- In progress
- Planned
- Not applicable
- Today
- Ideation
A similar need?
Nobody has come forward yet. If your team faces the same problem, say so: it helps bring initiatives together and share a solution.
Contacts
- Requester
- Quan, Eric
- Sector contact
- Chantelle Caron / Thomas Howey
- Subject matter expert
- Caron, Chantelle
Data and tools
- Region
- Pacific
- Submitted on
- May 29, 2025
Government priorities and declaration
- Prime Minister's mandate commitment
- Spending less on government operations so that Canadians can invest more in the people and businesses that will build the strongest economy in the G7.