What would it take to integrate support for symbol detection and conversion to SymPy for a single step in a derivation?
- user provides initial expression in Latex to web UI.
- computer parses symbols and operators from Latex
- computer searches Physics Derivation Graph database of symbols and operators to find candidate symbols
- computer provides candidate symbols to user and prompts, "which of the following symbols were you referring to?"
- computer parses expression to SymPy, returns AST to user, and prompts, "is this the AST you meant?"
- if yes, continue; if no, go back to step 1 or provide corrections to AST.
- user provides next expression in Latex
- computer parses symbols and operators from Latex
- if symbols match symbols used in this derivation, then associate with those; otherwise
- computer searches Physics Derivation Graph database of symbols and operators to find candidate symbols
- if computer had to search PDG database, then computer provides candidate symbols to user and prompts, "which of the following symbols were you referring to?"
- computer parses expression from step 7 to SymPy, returns AST to user, and prompts, "is this the AST you meant?"
- computer uses brute force to check every inference rule using a CAS against the provided expressions to "guess" the inference rule.
- if valid inference rule is found, continue to next expression; if no valid inference rule is found, prompt user to provide inference rule.
- Given the inference rule and associated expressions, use the CAS to verify the step.
No comments:
Post a Comment