results: s46 on Dicta test corpora — 0.52/0.24/0.45 DER (modern/poetry/rabbinic) - #73
Merged
Conversation
…oetry/rabbinic) The disclosed modern-text gap measured instead of skipped: line-level greedy DER on Dicta's three public-domain sets, dense GT (~0.8 marks/letter, not a sparsity artifact). s46 is strong across all three registers; the Hebrew weak surface is specifically the Nakdimon-style paragraph-level Biblical/Rabbinic test. Not directly comparable to D-Nikud's published DEC (token-level, their splits) — our-row-only per the ledger discipline.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
TODO.training-work/07 complete: the Hebrew modern-text surface measured. Line-level greedy DER on Dicta's three public-domain, densely-vocalized sets (density checked: ~0.8 marks/letter — the low DERs are not sparsity artifacts). s46 is strong across modern, poetry, and rabbinic registers; the weak surface is specifically the Nakdimon-style paragraph-level Biblical/Rabbinic test. Our-row-only per the ledger discipline (D-Nikud's DEC is token-level on their splits — not comparable without mapping). dicta_eval.json on the volume carries the raw result.