spaCy/website/docs/api/goldparse.jade

105 lines
2.4 KiB
Plaintext

//- 💫 DOCS > API > GOLDPARSE
include ../../_includes/_mixins
p Collection for training annotations.
+h(2, "init") GoldParse.__init__
+tag method
p Create a GoldParse.
+table(["Name", "Type", "Description"])
+row
+cell #[code doc]
+cell #[code Doc]
+cell The document the annotations refer to.
+row
+cell #[code words]
+cell -
+cell A sequence of unicode word strings.
+row
+cell #[code tags]
+cell -
+cell A sequence of strings, representing tag annotations.
+row
+cell #[code heads]
+cell -
+cell A sequence of integers, representing syntactic head offsets.
+row
+cell #[code deps]
+cell -
+cell A sequence of strings, representing the syntactic relation types.
+row
+cell #[code entities]
+cell -
+cell A sequence of named entity annotations, either as BILUO tag strings, or as #[code (start_char, end_char, label)] tuples, representing the entity positions.
+footrow
+cell returns
+cell #[code GoldParse]
+cell The newly constructed object.
+h(2, "len") GoldParse.__len__
+tag method
p Get the number of gold-standard tokens.
+table(["Name", "Type", "Description"])
+footrow
+cell returns
+cell int
+cell The number of gold-standard tokens.
+h(2, "is_projective") GoldParse.is_projective
+tag property
p
| Whether the provided syntactic annotations form a projective dependency
| tree.
+table(["Name", "Type", "Description"])
+footrow
+cell returns
+cell bool
+cell Whether annotations form projective tree.
+h(2, "attributes") Attributes
+table(["Name", "Type", "Description"])
+row
+cell #[code tags]
+cell list
+cell The part-of-speech tag annotations.
+row
+cell #[code heads]
+cell list
+cell The syntactic head annotations.
+row
+cell #[code labels]
+cell list
+cell The syntactic relation-type annotations.
+row
+cell #[code ents]
+cell list
+cell The named entity annotations.
+row
+cell #[code cand_to_gold]
+cell list
+cell The alignment from candidate tokenization to gold tokenization.
+row
+cell #[code gold_to_cand]
+cell list
+cell The alignment from gold tokenization to candidate tokenization.