Repository navigation
[LLM] Implement sentence readability scorer with level bucketing - #6
Merged
Merged
Conversation
Implement Step 4 of Pipeline 1 from INGESTION.md in SentenceScorer with BreakIterator tokenization, rarity ratio, cognate ratio, complex tense penalty, and level bucketing into Levels 0-2 or discard. Add comprehensive unit tests.
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Implements Step 4 of Pipeline 1 from
docs/INGESTION.md:SentenceScorer.tokenizeWords: Unicode-aware word tokenization usingjava.text.BreakIteratorfor Spanish.SentenceScorer.scoreSentence: Evaluates sentence difficulty based on word count (4..14), subtitle frequency rank (>1500 as rare), transparent cognate ratio, and subjunctive/conditional tenses (+3.0 penalty).LEVEL_0(<= 2.0),LEVEL_1(<= 4.0), orLEVEL_2(<= 6.5), discarding sentences outside length constraints or exceeding difficulty thresholds.SentenceScorerTestcovering length bounds, score calculations, edge cases, and Spanish punctuation.Verification
bazelisk run //:format.checkpassedbazelisk build --config=lint //...passedbazelisk test //...passed