mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-24 17:06:29 +03:00
Add descriptions to POS tagging scheme
This commit is contained in:
ines
parent
1570b83ee5
commit
fac3566aac
|
|
@ -1,136 +1,139 @@
|
|||
//- 💫 DOCS > API > ANNOTATION > POS TAGS
|
||||
|
||||
mixin pos-row(...row)
|
||||
+row
|
||||
each cell in row
|
||||
+cell
|
||||
each item in cell.split(" ")
|
||||
if item
|
||||
| #[code=item]
|
||||
+infobox("Tip")
|
||||
| In spaCy v1.8.3+, you can also use #[code spacy.explain()] to get the
|
||||
| description for the string representation of a tag. For example,
|
||||
| #[code spacy.explain("RB")] will return "adverb".
|
||||
|
||||
+h(3, "pos-tagging-english") English part-of-speech tag scheme
|
||||
|
||||
p
|
||||
| The part-of-speech tagger uses the
|
||||
| The English part-of-speech tagger uses the
|
||||
| #[+a("https://catalog.ldc.upenn.edu/LDC2013T19") OntoNotes 5] version of
|
||||
| the Penn Treebank tag set. We also map the tags to the simpler Google
|
||||
| Universal POS tag set.
|
||||
|
||||
+h(3, "pos-tagging-english") English part-of-speech tag scheme
|
||||
|
||||
+table(["Tag", "POS", "Morphology"])
|
||||
+pos-row("-LRB-", "PUNCT", "PunctType=brck PunctSide=ini")
|
||||
+pos-row("-PRB-", "PUNCT", "PunctType=brck PunctSide=fin")
|
||||
+pos-row(",", "PUNCT", "PunctType=comm")
|
||||
+pos-row(":", "PUNCT", "")
|
||||
+pos-row(".", "PUNCT", "PunctType=peri")
|
||||
+pos-row("''", "PUNCT", "PunctType=quot PunctSide=fin")
|
||||
+pos-row("\"\"", "PUNCT", "PunctType=quot PunctSide=fin")
|
||||
+pos-row("#", "SYM", "SymType=numbersign")
|
||||
+pos-row("``", "PUNCT", "PunctType=quot PunctSide=ini")
|
||||
+pos-row("$", "SYM", "SymType=currency")
|
||||
+pos-row("ADD", "X", "")
|
||||
+pos-row("AFX", "ADJ", "Hyph=yes")
|
||||
+pos-row("BES", "VERB", "")
|
||||
+pos-row("CC", "CONJ", "ConjType=coor")
|
||||
+pos-row("CD", "NUM", "NumType=card")
|
||||
+pos-row("DT", "DET", "")
|
||||
+pos-row("EX", "ADV", "AdvType=ex")
|
||||
+pos-row("FW", "X", "Foreign=yes")
|
||||
+pos-row("GW", "X", "")
|
||||
+pos-row("HVS", "VERB", "")
|
||||
+pos-row("HYPH", "PUNCT", "PunctType=dash")
|
||||
+pos-row("IN", "ADP", "")
|
||||
+pos-row("JJ", "ADJ", "Degree=pos")
|
||||
+pos-row("JJR", "ADJ", "Degree=comp")
|
||||
+pos-row("JJS", "ADJ", "Degree=sup")
|
||||
+pos-row("LS", "PUNCT", "NumType=ord")
|
||||
+pos-row("MD", "VERB", "VerbType=mod")
|
||||
+pos-row("NFP", "PUNCT", "")
|
||||
+pos-row("NIL", "", "")
|
||||
+pos-row("NN", "NOUN", "Number=sing")
|
||||
+pos-row("NNP", "PROPN", "NounType=prop Number=sign")
|
||||
+pos-row("NNPS", "PROPN", "NounType=prop Number=plur")
|
||||
+pos-row("NNS", "NOUN", "Number=plur")
|
||||
+pos-row("PDT", "ADJ", "AdjType=pdt PronType=prn")
|
||||
+pos-row("POS", "PART", "Poss=yes")
|
||||
+pos-row("PRP", "PRON", "PronType=prs")
|
||||
+pos-row("PRP$", "ADJ", "PronType=prs Poss=yes")
|
||||
+pos-row("RB", "ADV", "Degree=pos")
|
||||
+pos-row("RBR", "ADV", "Degree=comp")
|
||||
+pos-row("RBS", "ADV", "Degree=sup")
|
||||
+pos-row("RP", "PART", "")
|
||||
+pos-row("SP", "SPACE", "")
|
||||
+pos-row("SYM", "SYM", "")
|
||||
+pos-row("TO", "PART", "PartType=inf VerbForm=inf")
|
||||
+pos-row("UH", "INTJ", "")
|
||||
+pos-row("VB", "VERB", "VerbForm=inf")
|
||||
+pos-row("VBD", "VERB", "VerbForm=fin Tense=past")
|
||||
+pos-row("VBG", "VERB", "VerbForm=part Tense=pres Aspect=prog")
|
||||
+pos-row("VBN", "VERB", "VerbForm=part Tense=past Aspect=perf")
|
||||
+pos-row("VBP", "VERB", "VerbForm=fin Tense=pres")
|
||||
+pos-row("VBZ", "VERB", "VerbForm=fin Tense=pres Number=sing Person=3")
|
||||
+pos-row("WDT", "ADJ", "PronType=int|rel")
|
||||
+pos-row("WP", "NOUN", "PronType=int|rel")
|
||||
+pos-row("WP$", "ADJ", "Poss=yes PronType=int|rel")
|
||||
+pos-row("WRB", "ADV", "PronType=int|rel")
|
||||
+pos-row("XX", "X", "")
|
||||
+table(["Tag", "POS", "Morphology", "Description"])
|
||||
+pos-row("-LRB-", "PUNCT", "PunctType=brck PunctSide=ini", "left round bracket")
|
||||
+pos-row("-PRB-", "PUNCT", "PunctType=brck PunctSide=fin", "right round bracket")
|
||||
+pos-row(",", "PUNCT", "PunctType=comm", "punctuation mark, comma")
|
||||
+pos-row(":", "PUNCT", "", "punctuation mark, colon or ellipsis")
|
||||
+pos-row(".", "PUNCT", "PunctType=peri", "punctuation mark, sentence closer")
|
||||
+pos-row("''", "PUNCT", "PunctType=quot PunctSide=fin", "closing quotation mark")
|
||||
+pos-row("\"\"", "PUNCT", "PunctType=quot PunctSide=fin", "closing quotation mark")
|
||||
+pos-row("#", "SYM", "SymType=numbersign", "symbol, number sign")
|
||||
+pos-row("``", "PUNCT", "PunctType=quot PunctSide=ini", "opening quotation mark")
|
||||
+pos-row("$", "SYM", "SymType=currency", "symbol, currency")
|
||||
+pos-row("ADD", "X", "", "email")
|
||||
+pos-row("AFX", "ADJ", "Hyph=yes", "affix")
|
||||
+pos-row("BES", "VERB", "", 'auxillary "be"')
|
||||
+pos-row("CC", "CONJ", "ConjType=coor", "conjunction, coordinating")
|
||||
+pos-row("CD", "NUM", "NumType=card", "cardinal number")
|
||||
+pos-row("DT", "DET", "determiner")
|
||||
+pos-row("EX", "ADV", "AdvType=ex", "existential there")
|
||||
+pos-row("FW", "X", "Foreign=yes", "foreign word")
|
||||
+pos-row("GW", "X", "", "additional word in multi-word expression")
|
||||
+pos-row("HVS", "VERB", "", 'forms of "have"')
|
||||
+pos-row("HYPH", "PUNCT", "PunctType=dash", "punctuation mark, hyphen")
|
||||
+pos-row("IN", "ADP", "", "conjunction, subordinating or preposition")
|
||||
+pos-row("JJ", "ADJ", "Degree=pos", "adjective")
|
||||
+pos-row("JJR", "ADJ", "Degree=comp", "adjective, comparative")
|
||||
+pos-row("JJS", "ADJ", "Degree=sup", "adjective, superlative")
|
||||
+pos-row("LS", "PUNCT", "NumType=ord", "list item marker")
|
||||
+pos-row("MD", "VERB", "VerbType=mod", "verb, modal auxillary")
|
||||
+pos-row("NFP", "PUNCT", "", "superfluous punctuation")
|
||||
+pos-row("NIL", "", "", "missing tag")
|
||||
+pos-row("NN", "NOUN", "Number=sing", "noun, singular or mass")
|
||||
+pos-row("NNP", "PROPN", "NounType=prop Number=sign", "noun, proper singular")
|
||||
+pos-row("NNPS", "PROPN", "NounType=prop Number=plur", "noun, proper plural")
|
||||
+pos-row("NNS", "NOUN", "Number=plur", "noun, plural")
|
||||
+pos-row("PDT", "ADJ", "AdjType=pdt PronType=prn", "predeterminer")
|
||||
+pos-row("POS", "PART", "Poss=yes", "possessive ending")
|
||||
+pos-row("PRP", "PRON", "PronType=prs", "pronoun, personal")
|
||||
+pos-row("PRP$", "ADJ", "PronType=prs Poss=yes", "pronoun, possessive")
|
||||
+pos-row("RB", "ADV", "Degree=pos", "adverb")
|
||||
+pos-row("RBR", "ADV", "Degree=comp", "adverb, comparative")
|
||||
+pos-row("RBS", "ADV", "Degree=sup", "adverb, superlative")
|
||||
+pos-row("RP", "PART", "", "adverb, particle")
|
||||
+pos-row("SP", "SPACE", "", "space")
|
||||
+pos-row("SYM", "SYM", "", "symbol")
|
||||
+pos-row("TO", "PART", "PartType=inf VerbForm=inf", "infinitival to")
|
||||
+pos-row("UH", "INTJ", "", "interjection")
|
||||
+pos-row("VB", "VERB", "VerbForm=inf", "verb, base form")
|
||||
+pos-row("VBD", "VERB", "VerbForm=fin Tense=past", "verb, past tense")
|
||||
+pos-row("VBG", "VERB", "VerbForm=part Tense=pres Aspect=prog", "verb, gerund or present participle")
|
||||
+pos-row("VBN", "VERB", "VerbForm=part Tense=past Aspect=perf", "verb, past participle")
|
||||
+pos-row("VBP", "VERB", "VerbForm=fin Tense=pres", "verb, non-3rd person singular present")
|
||||
+pos-row("VBZ", "VERB", "VerbForm=fin Tense=pres Number=sing Person=3", "verb, 3rd person singular present")
|
||||
+pos-row("WDT", "ADJ", "PronType=int|rel", "wh-determiner")
|
||||
+pos-row("WP", "NOUN", "PronType=int|rel", "wh-pronoun, personal")
|
||||
+pos-row("WP$", "ADJ", "Poss=yes PronType=int|rel", "wh-pronoun, possessive")
|
||||
+pos-row("WRB", "ADV", "PronType=int|rel", "wh-adverb")
|
||||
+pos-row("XX", "X", "", "unknown")
|
||||
|
||||
+h(3, "pos-tagging-german") German part-of-speech tag scheme
|
||||
|
||||
+table(["Tag", "POS", "Morphology"])
|
||||
+pos-row("$(", "PUNCT", "PunctType=brck")
|
||||
+pos-row("$,", "PUNCT", "PunctType=comm")
|
||||
+pos-row("$.", "PUNCT", "PunctType=peri")
|
||||
+pos-row("ADJA", "ADJ", "")
|
||||
+pos-row("ADJD", "ADJ", "Variant=short")
|
||||
+pos-row("ADV", "ADV", "")
|
||||
+pos-row("APPO", "ADP", "AdpType=post")
|
||||
+pos-row("APPR", "ADP", "AdpType=prep")
|
||||
+pos-row("APPRART", "ADP", "AdpType=prep PronType=art")
|
||||
+pos-row("APZR", "ADP", "AdpType=circ")
|
||||
+pos-row("ART", "DET", "PronType=art")
|
||||
+pos-row("CARD", "NUM", "NumType=card")
|
||||
+pos-row("FM", "X", "Foreign=yes")
|
||||
+pos-row("ITJ", "INTJ", "")
|
||||
+pos-row("KOKOM", "CONJ", "ConjType=comp")
|
||||
+pos-row("KON", "CONJ", "")
|
||||
+pos-row("KOUI", "SCONJ", "")
|
||||
+pos-row("KOUS", "SCONJ", "")
|
||||
+pos-row("NE", "PROPN", "")
|
||||
+pos-row("NNE", "PROPN", "")
|
||||
+pos-row("NN", "NOUN", "")
|
||||
+pos-row("PAV", "ADV", "PronType=dem")
|
||||
+pos-row("PROAV", "ADV", "PronType=dem")
|
||||
+pos-row("PDAT", "DET", "PronType=dem")
|
||||
+pos-row("PDS", "PRON", "PronType=dem")
|
||||
+pos-row("PIAT", "DET", "PronType=ind|neg|tot")
|
||||
+pos-row("PIDAT", "DET", "AdjType=pdt PronType=ind|neg|tot")
|
||||
+pos-row("PIS", "PRON", "PronType=ind|neg|tot")
|
||||
+pos-row("PPER", "PRON", "PronType=prs")
|
||||
+pos-row("PPOSAT", "DET", "Poss=yes PronType=prs")
|
||||
+pos-row("PPOSS", "PRON", "PronType=rel")
|
||||
+pos-row("PRELAT", "DET", "PronType=rel")
|
||||
+pos-row("PRELS", "PRON", "PronType=rel")
|
||||
+pos-row("PRF", "PRON", "PronType=prs Reflex=yes")
|
||||
+pos-row("PTKA", "PART", "")
|
||||
+pos-row("PTKANT", "PART", "PartType=res")
|
||||
+pos-row("PTKNEG", "PART", "Negative=yes")
|
||||
+pos-row("PTKVZ", "PART", "PartType=vbp")
|
||||
+pos-row("PTKZU", "PART", "PartType=inf")
|
||||
+pos-row("PWAT", "DET", "PronType=int")
|
||||
+pos-row("PWAV", "ADV", "PronType=int")
|
||||
+pos-row("PWS", "PRON", "PronType=int")
|
||||
+pos-row("TRUNC", "X", "Hyph=yes")
|
||||
+pos-row("VAFIN", "AUX", "Mood=ind VerbForm=fin")
|
||||
+pos-row("VAIMP", "AUX", "Mood=imp VerbForm=fin")
|
||||
+pos-row("VAINF", "AUX", "VerbForm=inf")
|
||||
+pos-row("VAPP", "AUX", "Aspect=perf VerbForm=fin")
|
||||
+pos-row("VMFIN", "VERB", "Mood=ind VerbForm=fin VerbType=mod")
|
||||
+pos-row("VMINF", "VERB", "VerbForm=fin VerbType=mod")
|
||||
+pos-row("VMPP", "VERB", "Aspect=perf VerbForm=part VerbType=mod")
|
||||
+pos-row("VVFIN", "VERB", "Mood=ind VerbForm=fin")
|
||||
+pos-row("VVIMP", "VERB", "Mood=imp VerbForm=fin")
|
||||
+pos-row("VVINF", "VERB", "VerbForm=inf")
|
||||
+pos-row("VVIZU", "VERB", "VerbForm=inf")
|
||||
+pos-row("VVPP", "VERB", "Aspect=perf VerbForm=part")
|
||||
+pos-row("XY", "X", "")
|
||||
+pos-row("SP", "SPACE", "")
|
||||
p
|
||||
| The German part-of-speech tagger uses the
|
||||
| #[+a("http://www.ims.uni-stuttgart.de/forschung/ressourcen/korpora/TIGERCorpus/annotation/index.html") TIGER Treebank]
|
||||
| annotation scheme. We also map the tags to the simpler Google
|
||||
| Universal POS tag set.
|
||||
|
||||
+table(["Tag", "POS", "Morphology", "Description"])
|
||||
+pos-row("$(", "PUNCT", "PunctType=brck", "other sentence-internal punctuation mark")
|
||||
+pos-row("$,", "PUNCT", "PunctType=comm", "comma")
|
||||
+pos-row("$.", "PUNCT", "PunctType=peri", "sentence-final punctuation mark")
|
||||
+pos-row("ADJA", "ADJ", "", "adjective, attributive")
|
||||
+pos-row("ADJD", "ADJ", "Variant=short", "adjective, adverbial or predicative")
|
||||
+pos-row("ADV", "ADV", "", "adverb")
|
||||
+pos-row("APPO", "ADP", "AdpType=post", "postposition")
|
||||
+pos-row("APPR", "ADP", "AdpType=prep", "preposition; circumposition left")
|
||||
+pos-row("APPRART", "ADP", "AdpType=prep PronType=art", "preposition with article")
|
||||
+pos-row("APZR", "ADP", "AdpType=circ", "circumposition right")
|
||||
+pos-row("ART", "DET", "PronType=art", "definite or indefinite article")
|
||||
+pos-row("CARD", "NUM", "NumType=card", "cardinal number")
|
||||
+pos-row("FM", "X", "Foreign=yes", "foreign language material")
|
||||
+pos-row("ITJ", "INTJ", "", "interjection")
|
||||
+pos-row("KOKOM", "CONJ", "ConjType=comp", "comparative conjunction")
|
||||
+pos-row("KON", "CONJ", "", "coordinate conjunction")
|
||||
+pos-row("KOUI", "SCONJ", "", 'subordinate conjunction with "zu" and infinitive')
|
||||
+pos-row("KOUS", "SCONJ", "", "subordinate conjunction with sentence")
|
||||
+pos-row("NE", "PROPN", "", "proper noun")
|
||||
+pos-row("NNE", "PROPN", "", "proper noun")
|
||||
+pos-row("NN", "NOUN", "", "noun, singular or mass")
|
||||
+pos-row("PAV", "ADV", "PronType=dem", "pronominal adverb")
|
||||
+pos-row("PROAV", "ADV", "PronType=dem", "pronominal adverb")
|
||||
+pos-row("PDAT", "DET", "PronType=dem", "attributive demonstrative pronoun")
|
||||
+pos-row("PDS", "PRON", "PronType=dem", "substituting demonstrative pronoun")
|
||||
+pos-row("PIAT", "DET", "PronType=ind|neg|tot", "attributive indefinite pronoun without determiner")
|
||||
+pos-row("PIDAT", "DET", "AdjType=pdt PronType=ind|neg|tot", "attributive indefinite pronoun with determiner")
|
||||
+pos-row("PIS", "PRON", "PronType=ind|neg|tot", "substituting indefinite pronoun")
|
||||
+pos-row("PPER", "PRON", "PronType=prs", "non-reflexive personal pronoun")
|
||||
+pos-row("PPOSAT", "DET", "Poss=yes PronType=prs", "attributive possessive pronoun")
|
||||
+pos-row("PPOSS", "PRON", "PronType=rel", "substituting possessive pronoun")
|
||||
+pos-row("PRELAT", "DET", "PronType=rel", "attributive relative pronoun")
|
||||
+pos-row("PRELS", "PRON", "PronType=rel", "substituting relative pronoun")
|
||||
+pos-row("PRF", "PRON", "PronType=prs Reflex=yes", "reflexive personal pronoun")
|
||||
+pos-row("PTKA", "PART", "", "particle with adjective or adverb")
|
||||
+pos-row("PTKANT", "PART", "PartType=res", "answer particle")
|
||||
+pos-row("PTKNEG", "PART", "Negative=yes", "negative particle")
|
||||
+pos-row("PTKVZ", "PART", "PartType=vbp", "separable verbal particle")
|
||||
+pos-row("PTKZU", "PART", "PartType=inf", '"zu" before infinitive')
|
||||
+pos-row("PWAT", "DET", "PronType=int", "attributive interrogative pronoun")
|
||||
+pos-row("PWAV", "ADV", "PronType=int", "adverbial interrogative or relative pronoun")
|
||||
+pos-row("PWS", "PRON", "PronType=int", "substituting interrogative pronoun")
|
||||
+pos-row("TRUNC", "X", "Hyph=yes", "word remnant")
|
||||
+pos-row("VAFIN", "AUX", "Mood=ind VerbForm=fin", "finite verb, auxiliary")
|
||||
+pos-row("VAIMP", "AUX", "Mood=imp VerbForm=fin", "imperative, auxiliary")
|
||||
+pos-row("VAINF", "AUX", "VerbForm=inf", "infinitive, auxiliary")
|
||||
+pos-row("VAPP", "AUX", "Aspect=perf VerbForm=fin", "perfect participle, auxiliary")
|
||||
+pos-row("VMFIN", "VERB", "Mood=ind VerbForm=fin VerbType=mod", "finite verb, modal")
|
||||
+pos-row("VMINF", "VERB", "VerbForm=fin VerbType=mod", "infinitive, modal")
|
||||
+pos-row("VMPP", "VERB", "Aspect=perf VerbForm=part VerbType=mod", "perfect participle, modal")
|
||||
+pos-row("VVFIN", "VERB", "Mood=ind VerbForm=fin", "finite verb, full")
|
||||
+pos-row("VVIMP", "VERB", "Mood=imp VerbForm=fin", "imperative, full")
|
||||
+pos-row("VVINF", "VERB", "VerbForm=inf", "infinitive, full")
|
||||
+pos-row("VVIZU", "VERB", "VerbForm=inf", 'infinitive with "zu", full')
|
||||
+pos-row("VVPP", "VERB", "Aspect=perf VerbForm=part", "perfect participle, full")
|
||||
+pos-row("XY", "X", "", "non-word containing non-letter")
|
||||
+pos-row("SP", "SPACE", "", "space")
|
||||
|
|
|
|||
Loading…
Reference in New Issue
Block a user