Add embeddings space diagnostics: cohesion, overlap, and query/passag…#25
Merged
Conversation
…e gap analysis evaluate_embeddings.py now checks whether the NAF taxonomy is reflected in the embedding space (per-level sibling cohesion, a sorted similarity heatmap, inter-group confusion/overlap detection, retrieval confusion tally, and a query/passage gap diagnostic for libellés vs. notices), plus an experiment testing whether embedding the notices' "Excludes" text improves retrieval. Also publishes these diagnostics as a Quarto report (presentation/embeddings.qmd) alongside the existing presentation site, with a frozen execution cache so CI can render it without live access to the internal embedding API. Excludes presentation/_freeze/ from the large-file pre-commit check since that cache is expected to hold full rendered figure data. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
evaluate_embeddings.py now checks whether the NAF taxonomy is reflected in the embedding space (per-level sibling cohesion, a sorted similarity heatmap, inter-group confusion/overlap detection, retrieval confusion tally, and a query/passage gap diagnostic for libellés vs. notices), plus an experiment testing whether embedding the notices' "Excludes" text improves retrieval.
Also publishes these diagnostics as a Quarto report (presentation/embeddings.qmd) alongside the existing presentation site, with a frozen execution cache so CI can render it without live access to the internal embedding API. Excludes presentation/_freeze/ from the large-file pre-commit check since that cache is expected to hold full rendered figure data.