Repository navigation
Add SQL/PGQ prediction and Oracle evaluation support - #4
Open
oskar-van-rest wants to merge 5 commits into
Open
oskar-van-rest wants to merge 5 commits into
oskar-van-rest wants to merge 5 commits into
Conversation
…racy becausae those are not grammar issues but name/type resolution issues
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR extends the standalone Text2Graph workflow with ISO SQL/PGQ (ISO/IEC 9075-16) query generation and Oracle evaluation.
• Add sql_pgq as a prediction target with zero-shot and few-shot prompts, a required graph name, and schema input from SQL_PGQ/schema.txt.
• Add an Oracle evaluator for grammar accuracy using DBMS_SQL.PARSE and execution accuracy by comparing generated and gold query results.
• Treat selected Oracle name-resolution and semantic errors separately from grammar failures. Exclude failing gold queries from the execution-accuracy denominator.
• Integrate Oracle grammar evaluation into the existing similarity and Google BLEU workflow.
• Add the oracledb dependency and document connection setup and evaluator usage.