27 lines
837 B
YAML
27 lines
837 B
YAML
language: el
|
|
script: Greek
|
|
dialect: koine
|
|
|
|
normalization:
|
|
unicode_normal_form: NFC
|
|
lowercase_for_lookup: true
|
|
strip_diacritics: configurable
|
|
# Polytonic diacritics (breathing marks, accents, iota subscript) are
|
|
# preserved for morphological disambiguation but stripped for lemma lookup
|
|
polytonic_policy: preserve_for_morphology
|
|
diacritic_strip_for_lookup: true
|
|
|
|
punctuation:
|
|
strategy: preserve
|
|
ano_teleia: "\u00b7" # Greek semicolon (middle dot)
|
|
erotimatiko: ";"
|
|
|
|
spacing:
|
|
strategy: whitespace-delimited
|
|
|
|
aspect:
|
|
# Koine Greek verbal aspect is semantically load-bearing and must be
|
|
# distinguished from tense. Morphological analysis must surface aspect
|
|
# independently of temporal reference.
|
|
explicit_in_features: true
|
|
aspect_values: ["aorist", "present", "perfect", "imperfect", "pluperfect", "future"]
|