The problem
Finding the relevant clause in long documents is slow and keyword search misses synonyms.
What to build
Build a semantic search with highlighted passages and cross-references for a sample set of public documents.
Success looks like
Higher retrieval relevance than keyword search on a labelled query set and links to the exact passage.
Suggested technologies
- Embeddings
- Hybrid search
- Document parsing
- Re-ranking
- Evaluation
An original, independent statement. It is not an official Smart India Hackathon problem statement, and Arventiq Labs is not affiliated with or endorsed by that programme. The scenario is illustrative and does not describe any specific organisation. Free to use with credit.