From 2d59dd374bf80a3cc184703677848d5110991a87 Mon Sep 17 00:00:00 2001 From: ines Date: Sun, 5 Nov 2017 16:09:30 +0100 Subject: [PATCH] Use collapsible sections for pos/dep scheme and update Will ensure better overview as we add more schemes for more languages --- website/api/_annotation/_dep-labels.jade | 206 +++++++------- website/api/_annotation/_pos-tags.jade | 258 +++++++++--------- .../_dependency-parse.jade | 4 + .../_linguistic-features/_pos-tagging.jade | 2 + 4 files changed, 242 insertions(+), 228 deletions(-) diff --git a/website/api/_annotation/_dep-labels.jade b/website/api/_annotation/_dep-labels.jade index 427b2f53a..71fec0e50 100644 --- a/website/api/_annotation/_dep-labels.jade +++ b/website/api/_annotation/_dep-labels.jade @@ -1,108 +1,112 @@ //- 💫 DOCS > API > ANNOTATION > DEPENDENCY LABELS -+h(3, "dependency-parsing-english") English dependency labels - p - | The English dependency labels use the #[+a("http://www.clearnlp.com") ClearNLP] - | #[+a("http://www.mathcs.emory.edu/~choi/doc/clear-dependency-2012.pdf") CLEAR Style]. + | This section lists the syntactic dependency labels assigned by + | spaCy's #[+a("/models") models]. The individual labels are + | language-specific and depend on the training corpus. -+table(["Label", "Description"]) - +dep-row("acomp", "adjectival complement") - +dep-row("advcl", "adverbial clause modifier") - +dep-row("advmod", "adverbial modifier") - +dep-row("agent", "agent") - +dep-row("amod", "adjectival modifier") - +dep-row("appos", "appositional modifier") - +dep-row("attr", "attribute") - +dep-row("aux", "auxiliary") - +dep-row("auxpass", "auxiliary (passive)") - +dep-row("cc", "coordinating conjunction") - +dep-row("ccomp", "clausal complement") - +dep-row("complm", "complementizer") - +dep-row("conj", "conjunct") - +dep-row("cop", "copula") - +dep-row("csubj", "clausal subject") - +dep-row("csubjpass", "clausal subject (passive)") - +dep-row("dep", "unclassified dependent") - +dep-row("det", "determiner") - +dep-row("dobj", "direct object") - +dep-row("expl", "expletive") - +dep-row("hmod", "modifier in hyphenation") - +dep-row("hyph", "hyphen") - +dep-row("infmod", "infinitival modifier") - +dep-row("intj", "interjection") - +dep-row("iobj", "indirect object") - +dep-row("mark", "marker") - +dep-row("meta", "meta modifier") - +dep-row("neg", "negation modifier") - +dep-row("nmod", "modifier of nominal") - +dep-row("nn", "noun compound modifier") - +dep-row("npadvmod", "noun phrase as adverbial modifier") - +dep-row("nsubj", "nominal subject") - +dep-row("nsubjpass", "nominal subject (passive)") - +dep-row("num", "number modifier") - +dep-row("number", "number compound modifier") - +dep-row("oprd", "object predicate") - +dep-row("obj", "object") - +dep-row("obl", "oblique nominal") - +dep-row("parataxis", "parataxis") - +dep-row("partmod", "participal modifier") - +dep-row("pcomp", "complement of preposition") - +dep-row("pobj", "object of preposition") - +dep-row("poss", "possession modifier") - +dep-row("possessive", "possessive modifier") - +dep-row("preconj", "pre-correlative conjunction") - +dep-row("prep", "prepositional modifier") - +dep-row("prt", "particle") - +dep-row("punct", "punctuation") - +dep-row("quantmod", "modifier of quantifier") - +dep-row("rcmod", "relative clause modifier") - +dep-row("root", "root") - +dep-row("xcomp", "open clausal complement") ++accordion("English", "dependency-parsing-english") + p + | The English dependency labels use the + | #[+a("http://www.mathcs.emory.edu/~choi/doc/clear-dependency-2012.pdf") CLEAR Style] + | by #[+a("http://www.clearnlp.com") ClearNLP]. -+h(3, "dependency-parsing-german") German dependency labels + +table(["Label", "Description"]) + +dep-row("acomp", "adjectival complement") + +dep-row("advcl", "adverbial clause modifier") + +dep-row("advmod", "adverbial modifier") + +dep-row("agent", "agent") + +dep-row("amod", "adjectival modifier") + +dep-row("appos", "appositional modifier") + +dep-row("attr", "attribute") + +dep-row("aux", "auxiliary") + +dep-row("auxpass", "auxiliary (passive)") + +dep-row("cc", "coordinating conjunction") + +dep-row("ccomp", "clausal complement") + +dep-row("complm", "complementizer") + +dep-row("conj", "conjunct") + +dep-row("cop", "copula") + +dep-row("csubj", "clausal subject") + +dep-row("csubjpass", "clausal subject (passive)") + +dep-row("dep", "unclassified dependent") + +dep-row("det", "determiner") + +dep-row("dobj", "direct object") + +dep-row("expl", "expletive") + +dep-row("hmod", "modifier in hyphenation") + +dep-row("hyph", "hyphen") + +dep-row("infmod", "infinitival modifier") + +dep-row("intj", "interjection") + +dep-row("iobj", "indirect object") + +dep-row("mark", "marker") + +dep-row("meta", "meta modifier") + +dep-row("neg", "negation modifier") + +dep-row("nmod", "modifier of nominal") + +dep-row("nn", "noun compound modifier") + +dep-row("npadvmod", "noun phrase as adverbial modifier") + +dep-row("nsubj", "nominal subject") + +dep-row("nsubjpass", "nominal subject (passive)") + +dep-row("num", "number modifier") + +dep-row("number", "number compound modifier") + +dep-row("oprd", "object predicate") + +dep-row("obj", "object") + +dep-row("obl", "oblique nominal") + +dep-row("parataxis", "parataxis") + +dep-row("partmod", "participal modifier") + +dep-row("pcomp", "complement of preposition") + +dep-row("pobj", "object of preposition") + +dep-row("poss", "possession modifier") + +dep-row("possessive", "possessive modifier") + +dep-row("preconj", "pre-correlative conjunction") + +dep-row("prep", "prepositional modifier") + +dep-row("prt", "particle") + +dep-row("punct", "punctuation") + +dep-row("quantmod", "modifier of quantifier") + +dep-row("rcmod", "relative clause modifier") + +dep-row("root", "root") + +dep-row("xcomp", "open clausal complement") -p - | The German dependency labels use the - | #[+a("http://www.ims.uni-stuttgart.de/forschung/ressourcen/korpora/TIGERCorpus/annotation/index.html") TIGER Treebank] - | annotation scheme. ++accordion("German", "dependency-parsing-german") + p + | The German dependency labels use the + | #[+a("http://www.ims.uni-stuttgart.de/forschung/ressourcen/korpora/TIGERCorpus/annotation/index.html") TIGER Treebank] + | annotation scheme. -+table(["Label", "Description"]) - +dep-row("ac", "adpositional case marker") - +dep-row("adc", "adjective component") - +dep-row("ag", "genitive attribute") - +dep-row("ams", "measure argument of adjective") - +dep-row("app", "apposition") - +dep-row("avc", "adverbial phrase component") - +dep-row("cc", "comparative complement") - +dep-row("cd", "coordinating conjunction") - +dep-row("cj", "conjunct") - +dep-row("cm", "comparative conjunction") - +dep-row("cp", "complementizer") - +dep-row("cvc", "collocational verb construction") - +dep-row("da", "dative") - +dep-row("dh", "discourse-level head") - +dep-row("dm", "discourse marker") - +dep-row("ep", "expletive es") - +dep-row("hd", "head") - +dep-row("ju", "junctor") - +dep-row("mnr", "postnominal modifier") - +dep-row("mo", "modifier") - +dep-row("ng", "negation") - +dep-row("nk", "noun kernel element") - +dep-row("nmc", "numerical component") - +dep-row("oa", "accusative object") - +dep-row("oa", "second accusative object") - +dep-row("oc", "clausal object") - +dep-row("og", "genitive object") - +dep-row("op", "prepositional object") - +dep-row("par", "parenthetical element") - +dep-row("pd", "predicate") - +dep-row("pg", "phrasal genitive") - +dep-row("ph", "placeholder") - +dep-row("pm", "morphological particle") - +dep-row("pnc", "proper noun component") - +dep-row("rc", "relative clause") - +dep-row("re", "repeated element") - +dep-row("rs", "reported speech") - +dep-row("sb", "subject") + +table(["Label", "Description"]) + +dep-row("ac", "adpositional case marker") + +dep-row("adc", "adjective component") + +dep-row("ag", "genitive attribute") + +dep-row("ams", "measure argument of adjective") + +dep-row("app", "apposition") + +dep-row("avc", "adverbial phrase component") + +dep-row("cc", "comparative complement") + +dep-row("cd", "coordinating conjunction") + +dep-row("cj", "conjunct") + +dep-row("cm", "comparative conjunction") + +dep-row("cp", "complementizer") + +dep-row("cvc", "collocational verb construction") + +dep-row("da", "dative") + +dep-row("dh", "discourse-level head") + +dep-row("dm", "discourse marker") + +dep-row("ep", "expletive es") + +dep-row("hd", "head") + +dep-row("ju", "junctor") + +dep-row("mnr", "postnominal modifier") + +dep-row("mo", "modifier") + +dep-row("ng", "negation") + +dep-row("nk", "noun kernel element") + +dep-row("nmc", "numerical component") + +dep-row("oa", "accusative object") + +dep-row("oa", "second accusative object") + +dep-row("oc", "clausal object") + +dep-row("og", "genitive object") + +dep-row("op", "prepositional object") + +dep-row("par", "parenthetical element") + +dep-row("pd", "predicate") + +dep-row("pg", "phrasal genitive") + +dep-row("ph", "placeholder") + +dep-row("pm", "morphological particle") + +dep-row("pnc", "proper noun component") + +dep-row("rc", "relative clause") + +dep-row("re", "repeated element") + +dep-row("rs", "reported speech") + +dep-row("sb", "subject") diff --git a/website/api/_annotation/_pos-tags.jade b/website/api/_annotation/_pos-tags.jade index 51db4f4e2..ad878633f 100644 --- a/website/api/_annotation/_pos-tags.jade +++ b/website/api/_annotation/_pos-tags.jade @@ -1,134 +1,138 @@ //- 💫 DOCS > API > ANNOTATION > POS TAGS -+h(3, "pos-tagging-english") English part-of-speech tag scheme - p - | 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. + | This section lists the fine-grained and coarse-grained part-of-speech + | tags assigned by spaCy's #[+a("/models") models]. The individual mapping + | 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]]. -+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("$", "SYM", "SymType=currency", "symbol, currency") - +pos-row("ADD", "X", "", "email") - +pos-row("AFX", "ADJ", "Hyph=yes", "affix") - +pos-row("BES", "VERB", "", 'auxiliary "be"') - +pos-row("CC", "CONJ", "ConjType=coor", "conjunction, coordinating") - +pos-row("CD", "NUM", "NumType=card", "cardinal number") - +pos-row("DT", "DET", "determiner") - +pos-row("EX", "ADV", "AdvType=ex", "existential there") - +pos-row("FW", "X", "Foreign=yes", "foreign word") - +pos-row("GW", "X", "", "additional word in multi-word expression") - +pos-row("HVS", "VERB", "", 'forms of "have"') - +pos-row("HYPH", "PUNCT", "PunctType=dash", "punctuation mark, hyphen") - +pos-row("IN", "ADP", "", "conjunction, subordinating or preposition") - +pos-row("JJ", "ADJ", "Degree=pos", "adjective") - +pos-row("JJR", "ADJ", "Degree=comp", "adjective, comparative") - +pos-row("JJS", "ADJ", "Degree=sup", "adjective, superlative") - +pos-row("LS", "PUNCT", "NumType=ord", "list item marker") - +pos-row("MD", "VERB", "VerbType=mod", "verb, modal auxiliary") - +pos-row("NFP", "PUNCT", "", "superfluous punctuation") - +pos-row("NIL", "", "", "missing tag") - +pos-row("NN", "NOUN", "Number=sing", "noun, singular or mass") - +pos-row("NNP", "PROPN", "NounType=prop Number=sign", "noun, proper singular") - +pos-row("NNPS", "PROPN", "NounType=prop Number=plur", "noun, proper plural") - +pos-row("NNS", "NOUN", "Number=plur", "noun, plural") - +pos-row("PDT", "ADJ", "AdjType=pdt PronType=prn", "predeterminer") - +pos-row("POS", "PART", "Poss=yes", "possessive ending") - +pos-row("PRP", "PRON", "PronType=prs", "pronoun, personal") - +pos-row("PRP$", "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$", "ADJ", "Poss=yes PronType=int|rel", "wh-pronoun, possessive") - +pos-row("WRB", "ADV", "PronType=int|rel", "wh-adverb") - +pos-row("XX", "X", "", "unknown") ++accordion("English", "pos-tagging-english") + p + | The English part-of-speech tagger uses the + | #[+a("https://catalog.ldc.upenn.edu/LDC2013T19") OntoNotes 5] version of + | the Penn Treebank tag set. We also map the tags to the simpler Google + | Universal POS tag set. -+h(3, "pos-tagging-german") German part-of-speech tag scheme + +table(["Tag", "POS", "Morphology", "Description"]) + +pos-row("-LRB-", "PUNCT", "PunctType=brck PunctSide=ini", "left round bracket") + +pos-row("-PRB-", "PUNCT", "PunctType=brck PunctSide=fin", "right round bracket") + +pos-row(",", "PUNCT", "PunctType=comm", "punctuation mark, comma") + +pos-row(":", "PUNCT", "", "punctuation mark, colon or ellipsis") + +pos-row(".", "PUNCT", "PunctType=peri", "punctuation mark, sentence closer") + +pos-row("''", "PUNCT", "PunctType=quot PunctSide=fin", "closing quotation mark") + +pos-row("\"\"", "PUNCT", "PunctType=quot PunctSide=fin", "closing quotation mark") + +pos-row("#", "SYM", "SymType=numbersign", "symbol, number sign") + +pos-row("``", "PUNCT", "PunctType=quot PunctSide=ini", "opening quotation mark") + +pos-row("$", "SYM", "SymType=currency", "symbol, currency") + +pos-row("ADD", "X", "", "email") + +pos-row("AFX", "ADJ", "Hyph=yes", "affix") + +pos-row("BES", "VERB", "", 'auxiliary "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 auxiliary") + +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") -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. ++accordion("German", "pos-tagging-german") + 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") + +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") diff --git a/website/usage/_linguistic-features/_dependency-parse.jade b/website/usage/_linguistic-features/_dependency-parse.jade index fa14aed09..c26d18095 100644 --- a/website/usage/_linguistic-features/_dependency-parse.jade +++ b/website/usage/_linguistic-features/_dependency-parse.jade @@ -181,6 +181,10 @@ p +annotation-row(["their", "ADJ", "poss", "requests"], style) +annotation-row(["requests", "NOUN", "dobj", "submit"], style) ++h(3, "dep-scheme") Dependency label scheme + +include ../../api/_annotation/_dep-labels + +h(3, "displacy") Visualizing dependencies p diff --git a/website/usage/_linguistic-features/_pos-tagging.jade b/website/usage/_linguistic-features/_pos-tagging.jade index 569828634..2639b0224 100644 --- a/website/usage/_linguistic-features/_pos-tagging.jade +++ b/website/usage/_linguistic-features/_pos-tagging.jade @@ -68,4 +68,6 @@ p | list-based exception files, acquired from | #[+a("https://wordnet.princeton.edu/") WordNet]. ++h(3, "pos-scheme") Part-of-speech tag scheme + include ../../api/_annotation/_pos-tags