Skip to content

Commit a6ffa94

Browse files
inesines
committed
Update UD schemes
1 parent 975e104 commit a6ffa94

File tree

3 files changed

+68
-23
lines changed

3 files changed

+68
-23
lines changed

‎website/_includes/_mixins.jade

Lines changed: 4 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -543,12 +543,13 @@ mixin pos-row(tag, pos, morph, desc)
543543
| #[code=m]
544544
+cell.u-text-small=desc
545545

546-
mixin univ-pos-row(tag, desc, example)
546+
mixin ud-row(tag, desc, example)
547547
+row
548548
+cell #[code=tag]
549549
+cell.u-text-small=desc
550-
+cell.u-text-small
551-
em=example
550+
if example
551+
+cell.u-text-small
552+
em=example
552553

553554
mixin dep-row(label, desc)
554555
+row

‎website/api/_annotation/_dep-labels.jade

Lines changed: 44 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -5,6 +5,50 @@ p
55
| spaCy's #[+a("/models") models]. The individual labels are
66
| language-specific and depend on the training corpus.
77

8+
+accordion("Universal Dependency Labels")
9+
p
10+
| The #[+a("http://universaldependencies.org/u/dep/") Universal Dependencies scheme]
11+
| is used in all languages trained on Universal Dependency Corpora.
12+
13+
+table(["Dep", "Description"])
14+
+ud-row("acl", "clausal modifier of noun (adjectival clause)")
15+
+ud-row("advcl", "adverbial clause modifier")
16+
+ud-row("advmod", "adverbial modifier")
17+
+ud-row("amod", "adjectival modifier")
18+
+ud-row("appos", "appositional modifier")
19+
+ud-row("aux", "auxiliary")
20+
+ud-row("case", "case marking")
21+
+ud-row("cc", "coordinating conjunction")
22+
+ud-row("ccomp", "clausal complement")
23+
+ud-row("clf", "classifier")
24+
+ud-row("compound", "compound")
25+
+ud-row("conj", "conjunct")
26+
+ud-row("cop", "copula")
27+
+ud-row("csubj", "clausal subject")
28+
+ud-row("dep", "unspecified dependency")
29+
+ud-row("det", "determiner")
30+
+ud-row("discourse", "discourse element")
31+
+ud-row("dislocated", "dislocated elements")
32+
+ud-row("expl", "expletive")
33+
+ud-row("fixed", "fixed multiword expression")
34+
+ud-row("flat", "flat multiword expression")
35+
+ud-row("goeswith", "goes with")
36+
+ud-row("iobj", "indirect object")
37+
+ud-row("list", "list")
38+
+ud-row("mark", "marker")
39+
+ud-row("nmod", "nominal modifier")
40+
+ud-row("nsubj", "nominal subject")
41+
+ud-row("nummod", "numeric modifier")
42+
+ud-row("obj", "object")
43+
+ud-row("obl", "oblique nominal")
44+
+ud-row("orphan", "orphan")
45+
+ud-row("parataxis", "parataxis")
46+
+ud-row("punct", "punctuation")
47+
+ud-row("reparandum", "overridden disfluency")
48+
+ud-row("root", "root")
49+
+ud-row("vocative", "vocative")
50+
+ud-row("xcomp", "open clausal complement")
51+
852
+accordion("English", "dependency-parsing-english")
953
p
1054
| The English dependency labels use the

‎website/api/_annotation/_pos-tags.jade

Lines changed: 20 additions & 20 deletions
Original file line numberDiff line numberDiff line change
@@ -6,7 +6,7 @@ p
66
| is specific to the training corpus and can be defined in the respective
77
| language data's #[+a("/usage/adding-languages#tag-map") #[code tag_map.py]].
88

9-
+accordion("Universal part-of-speech tags")
9+
+accordion("Universal Part-of-speech Tags")
1010
p
1111
| spaCy also maps all language-specific part-of-speech tags to a small,
1212
| fixed set of word type tags following the
@@ -17,25 +17,25 @@ p
1717
| #[+api("token#attributes") #[code Token.pos_]] attributes.
1818

1919
+table(["POS", "Description", "Examples"])
20-
+univ-pos-row("ADJ", "adjective", "big, old, green, incomprehensible, first")
21-
+univ-pos-row("ADP", "adposition", "in, to, during")
22-
+univ-pos-row("ADV", "adverb", "very, tomorrow, down, where, there")
23-
+univ-pos-row("AUX", "auxiliary", "is, has (done), will (do), should (do)")
24-
+univ-pos-row("CONJ", "conjunction", "and, or, but")
25-
+univ-pos-row("CCONJ", "coordinating conjunction", "and, or, but")
26-
+univ-pos-row("DET", "determiner", "a, an, the")
27-
+univ-pos-row("INTJ", "interjection", "psst, ouch, bravo, hello")
28-
+univ-pos-row("NOUN", "noun", "girl, cat, tree, air, beauty")
29-
+univ-pos-row("NUM", "numeral", "1, 2017, one, seventy-seven, IV, MMXIV")
30-
+univ-pos-row("PART", "particle", "'s, not, ")
31-
+univ-pos-row("PRON", "pronoun", "I, you, he, she, myself, themselves, somebody")
32-
+univ-pos-row("PROPN", "proper noun", "Mary, John, Londin, NATO, HBO")
33-
+univ-pos-row("PUNCT", "punctuation", "., (, ), ?")
34-
+univ-pos-row("SCONJ", "subordinating conjunction", "if, while, that")
35-
+univ-pos-row("SYM", "symbol", "$, %, §, ©, +, −, ×, ÷, =, :), 😝")
36-
+univ-pos-row("VERB", "verb", "run, runs, running, eat, ate, eating")
37-
+univ-pos-row("X", "other", "sfpksdpsxmsa")
38-
+univ-pos-row("SPACE", "space", "")
20+
+ud-row("ADJ", "adjective", "big, old, green, incomprehensible, first")
21+
+ud-row("ADP", "adposition", "in, to, during")
22+
+ud-row("ADV", "adverb", "very, tomorrow, down, where, there")
23+
+ud-row("AUX", "auxiliary", "is, has (done), will (do), should (do)")
24+
+ud-row("CONJ", "conjunction", "and, or, but")
25+
+ud-row("CCONJ", "coordinating conjunction", "and, or, but")
26+
+ud-row("DET", "determiner", "a, an, the")
27+
+ud-row("INTJ", "interjection", "psst, ouch, bravo, hello")
28+
+ud-row("NOUN", "noun", "girl, cat, tree, air, beauty")
29+
+ud-row("NUM", "numeral", "1, 2017, one, seventy-seven, IV, MMXIV")
30+
+ud-row("PART", "particle", "'s, not, ")
31+
+ud-row("PRON", "pronoun", "I, you, he, she, myself, themselves, somebody")
32+
+ud-row("PROPN", "proper noun", "Mary, John, Londin, NATO, HBO")
33+
+ud-row("PUNCT", "punctuation", "., (, ), ?")
34+
+ud-row("SCONJ", "subordinating conjunction", "if, while, that")
35+
+ud-row("SYM", "symbol", "$, %, §, ©, +, −, ×, ÷, =, :), 😝")
36+
+ud-row("VERB", "verb", "run, runs, running, eat, ate, eating")
37+
+ud-row("X", "other", "sfpksdpsxmsa")
38+
+ud-row("SPACE", "space", "")
3939

4040
+accordion("English", "pos-en")
4141
p

0 commit comments

Comments
 (0)