cjber / cdrc-semantic-search

The CDRC Semantic Search System is a project designed to enhance the search capabilities of the Centre for Consumer Data Research (CDRC) data catalogue.
2 stars 0 forks source link

Evaluate model performance using existing queries #2

Open cjber opened 6 months ago

cjber commented 6 months ago

There is a list of existing queries that use the CDRC keyword-based search. Evaluation could make use of these.

  1. Find most common searches and compare semantic search results to website results.
    • List retrieved datasets
  2. Should semantic search encourage longer form questioning? e.g. 'which datasets could help study diabetes?' rather than 'diabetes'.

It is worth noting that the most frequent queries tend to search with a known dataset in mind, e.g. 'imd', 'ahah'. Semantic search would be more focussed on dataset discovery.