langchain_experimental.data_anonymizer.deanonymizer_matching_strategies.combined_exact_fuzzy_matching_strategy¶

langchain_experimental.data_anonymizer.deanonymizer_matching_strategies.combined_exact_fuzzy_matching_strategy(text: str, deanonymizer_mapping: Dict[str, Dict[str, str]], max_l_dist: int = 3) str[source]¶

Combined exact and fuzzy matching strategy for deanonymization.

It is a RECOMMENDED STRATEGY.

Parameters
  • text (str) – text to deanonymize

  • deanonymizer_mapping (Dict[str, Dict[str, str]]) – mapping between anonymized entities and original ones

  • max_l_dist (int) – maximum Levenshtein distance between the anonymized entity and the text segment to consider it a match

Return type

str

Examples of matching:

Kaenu Reves -> Keanu Reeves John F. Kennedy -> John Kennedy