language: en script: Latin normalization: unicode_normal_form: NFC lowercase_for_lookup: true strip_diacritics: false punctuation: strategy: preserve sentence_terminals: [".", "!", "?"] quotation_marks: ["\u201c", "\u201d", "\u2018", "\u2019"] spacing: strategy: whitespace-delimited collapse_multiple_spaces: true special_forms: contractions: expand # "don't" -> "do not" before lemmatization # "it's" -> "it is" before lemmatization