mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 04:08:09 +03:00
Update UD schemes
This commit is contained in:
parent
975e1042ff
commit
a6ffa942bb
|
@ -543,10 +543,11 @@ mixin pos-row(tag, pos, morph, desc)
|
|||
| #[code=m]
|
||||
+cell.u-text-small=desc
|
||||
|
||||
mixin univ-pos-row(tag, desc, example)
|
||||
mixin ud-row(tag, desc, example)
|
||||
+row
|
||||
+cell #[code=tag]
|
||||
+cell.u-text-small=desc
|
||||
if example
|
||||
+cell.u-text-small
|
||||
em=example
|
||||
|
||||
|
|
|
@ -5,6 +5,50 @@ p
|
|||
| spaCy's #[+a("/models") models]. The individual labels are
|
||||
| language-specific and depend on the training corpus.
|
||||
|
||||
+accordion("Universal Dependency Labels")
|
||||
p
|
||||
| The #[+a("http://universaldependencies.org/u/dep/") Universal Dependencies scheme]
|
||||
| is used in all languages trained on Universal Dependency Corpora.
|
||||
|
||||
+table(["Dep", "Description"])
|
||||
+ud-row("acl", "clausal modifier of noun (adjectival clause)")
|
||||
+ud-row("advcl", "adverbial clause modifier")
|
||||
+ud-row("advmod", "adverbial modifier")
|
||||
+ud-row("amod", "adjectival modifier")
|
||||
+ud-row("appos", "appositional modifier")
|
||||
+ud-row("aux", "auxiliary")
|
||||
+ud-row("case", "case marking")
|
||||
+ud-row("cc", "coordinating conjunction")
|
||||
+ud-row("ccomp", "clausal complement")
|
||||
+ud-row("clf", "classifier")
|
||||
+ud-row("compound", "compound")
|
||||
+ud-row("conj", "conjunct")
|
||||
+ud-row("cop", "copula")
|
||||
+ud-row("csubj", "clausal subject")
|
||||
+ud-row("dep", "unspecified dependency")
|
||||
+ud-row("det", "determiner")
|
||||
+ud-row("discourse", "discourse element")
|
||||
+ud-row("dislocated", "dislocated elements")
|
||||
+ud-row("expl", "expletive")
|
||||
+ud-row("fixed", "fixed multiword expression")
|
||||
+ud-row("flat", "flat multiword expression")
|
||||
+ud-row("goeswith", "goes with")
|
||||
+ud-row("iobj", "indirect object")
|
||||
+ud-row("list", "list")
|
||||
+ud-row("mark", "marker")
|
||||
+ud-row("nmod", "nominal modifier")
|
||||
+ud-row("nsubj", "nominal subject")
|
||||
+ud-row("nummod", "numeric modifier")
|
||||
+ud-row("obj", "object")
|
||||
+ud-row("obl", "oblique nominal")
|
||||
+ud-row("orphan", "orphan")
|
||||
+ud-row("parataxis", "parataxis")
|
||||
+ud-row("punct", "punctuation")
|
||||
+ud-row("reparandum", "overridden disfluency")
|
||||
+ud-row("root", "root")
|
||||
+ud-row("vocative", "vocative")
|
||||
+ud-row("xcomp", "open clausal complement")
|
||||
|
||||
+accordion("English", "dependency-parsing-english")
|
||||
p
|
||||
| The English dependency labels use the
|
||||
|
|
|
@ -6,7 +6,7 @@ p
|
|||
| is specific to the training corpus and can be defined in the respective
|
||||
| language data's #[+a("/usage/adding-languages#tag-map") #[code tag_map.py]].
|
||||
|
||||
+accordion("Universal part-of-speech tags")
|
||||
+accordion("Universal Part-of-speech Tags")
|
||||
p
|
||||
| spaCy also maps all language-specific part-of-speech tags to a small,
|
||||
| fixed set of word type tags following the
|
||||
|
@ -17,25 +17,25 @@ p
|
|||
| #[+api("token#attributes") #[code Token.pos_]] attributes.
|
||||
|
||||
+table(["POS", "Description", "Examples"])
|
||||
+univ-pos-row("ADJ", "adjective", "big, old, green, incomprehensible, first")
|
||||
+univ-pos-row("ADP", "adposition", "in, to, during")
|
||||
+univ-pos-row("ADV", "adverb", "very, tomorrow, down, where, there")
|
||||
+univ-pos-row("AUX", "auxiliary", "is, has (done), will (do), should (do)")
|
||||
+univ-pos-row("CONJ", "conjunction", "and, or, but")
|
||||
+univ-pos-row("CCONJ", "coordinating conjunction", "and, or, but")
|
||||
+univ-pos-row("DET", "determiner", "a, an, the")
|
||||
+univ-pos-row("INTJ", "interjection", "psst, ouch, bravo, hello")
|
||||
+univ-pos-row("NOUN", "noun", "girl, cat, tree, air, beauty")
|
||||
+univ-pos-row("NUM", "numeral", "1, 2017, one, seventy-seven, IV, MMXIV")
|
||||
+univ-pos-row("PART", "particle", "'s, not, ")
|
||||
+univ-pos-row("PRON", "pronoun", "I, you, he, she, myself, themselves, somebody")
|
||||
+univ-pos-row("PROPN", "proper noun", "Mary, John, Londin, NATO, HBO")
|
||||
+univ-pos-row("PUNCT", "punctuation", "., (, ), ?")
|
||||
+univ-pos-row("SCONJ", "subordinating conjunction", "if, while, that")
|
||||
+univ-pos-row("SYM", "symbol", "$, %, §, ©, +, −, ×, ÷, =, :), 😝")
|
||||
+univ-pos-row("VERB", "verb", "run, runs, running, eat, ate, eating")
|
||||
+univ-pos-row("X", "other", "sfpksdpsxmsa")
|
||||
+univ-pos-row("SPACE", "space", "")
|
||||
+ud-row("ADJ", "adjective", "big, old, green, incomprehensible, first")
|
||||
+ud-row("ADP", "adposition", "in, to, during")
|
||||
+ud-row("ADV", "adverb", "very, tomorrow, down, where, there")
|
||||
+ud-row("AUX", "auxiliary", "is, has (done), will (do), should (do)")
|
||||
+ud-row("CONJ", "conjunction", "and, or, but")
|
||||
+ud-row("CCONJ", "coordinating conjunction", "and, or, but")
|
||||
+ud-row("DET", "determiner", "a, an, the")
|
||||
+ud-row("INTJ", "interjection", "psst, ouch, bravo, hello")
|
||||
+ud-row("NOUN", "noun", "girl, cat, tree, air, beauty")
|
||||
+ud-row("NUM", "numeral", "1, 2017, one, seventy-seven, IV, MMXIV")
|
||||
+ud-row("PART", "particle", "'s, not, ")
|
||||
+ud-row("PRON", "pronoun", "I, you, he, she, myself, themselves, somebody")
|
||||
+ud-row("PROPN", "proper noun", "Mary, John, Londin, NATO, HBO")
|
||||
+ud-row("PUNCT", "punctuation", "., (, ), ?")
|
||||
+ud-row("SCONJ", "subordinating conjunction", "if, while, that")
|
||||
+ud-row("SYM", "symbol", "$, %, §, ©, +, −, ×, ÷, =, :), 😝")
|
||||
+ud-row("VERB", "verb", "run, runs, running, eat, ate, eating")
|
||||
+ud-row("X", "other", "sfpksdpsxmsa")
|
||||
+ud-row("SPACE", "space", "")
|
||||
|
||||
+accordion("English", "pos-en")
|
||||
p
|
||||
|
|
Loading…
Reference in New Issue
Block a user