Nils Diewald | 023c671 | 2015-05-21 20:12:30 +0000 | [diff] [blame] | 1 | var menuContent = [ |
| 2 | ['cnx/c', 'cnx', 'c'], |
| 3 | ['mate/c', 'mate', 'c'], |
| 4 | ['base/c', 'base', 'c'], |
| 5 | ['xip/c', 'xip', 'c'], |
| 6 | ['tt/c', 'tt', 'c'] |
| 7 | ]; |
| 8 | |
| 9 | var namedEntities = [ |
| 10 | ["I-LOC", "I-LOC ", "Location"], |
| 11 | ["I-MISC", "I-MISC ", "Miscellaneous"], |
| 12 | ["I-ORG", "I-ORG ", "Organization"], |
| 13 | ["I-PER", "I-PER ", "Person"] |
| 14 | ]; |
| 15 | |
| 16 | // http://www.ids-mannheim.de/cosmas2/projekt/referenz/stts/morph.html |
| 17 | // http://nachhalt.sfb632.uni-potsdam.de/owl-docu/stts.html |
| 18 | var sttsArray = [ |
| 19 | // "$.", "$(", "$," |
| 20 | ["ADJA","ADJA ", "Attributive Adjective"], |
| 21 | ["ADJD","ADJD ", "Predicative Adjective"], |
| 22 | ["ADV","ADV ", "Adverb"], |
| 23 | ["APPO","APPO ", "Postposition"], |
| 24 | ["APPR","APPR ", "Preposition"], |
| 25 | ["APPRART","APPRART ", "Preposition with Determiner"], |
| 26 | ["APZR","APZR ","Right Circumposition"], |
| 27 | ["ART","ART ", "Determiner"], |
| 28 | ["CARD","CARD ", "Cardinal Number"], |
| 29 | ["FM","FM ", "Foreign Material"], |
| 30 | ["ITJ","ITJ ", "Interjection"], |
| 31 | ["KOKOM","KOKOM ", "Comparison Particle"], |
| 32 | ["KON","KON ", "Coordinating Conjuncion"], |
| 33 | ["KOUI","KOUI ", "Subordinating Conjunction with 'zu'"], |
| 34 | ["KOUS","KOUS ", "Subordinating Conjunction with Sentence"], |
| 35 | ["NE","NE ", "Named Entity"], |
| 36 | ["NN","NN ", "Normal Nomina"], |
| 37 | ["PAV", "PAV ", "Pronominal Adverb"], |
| 38 | ["PDAT","PDAT ","Attributive Demonstrative Pronoun"], |
| 39 | ["PDS","PDS ", "Substitutive Demonstrative Pronoun"], |
| 40 | ["PIAT","PIAT ", "Attributive Indefinite Pronoun without Determiner"], |
| 41 | ["PIDAT","PIDAT ", "Attributive Indefinite Pronoun with Determiner"], |
| 42 | ["PIS","PIS ", "Substitutive Indefinite Pronoun"], |
| 43 | ["PPER","PPER ", "Personal Pronoun"], |
| 44 | ["PPOSAT","PPOSAT ", "Attributive Possessive Pronoun"], |
| 45 | ["PPOSS","PPOSS ", "Substitutive Possessive Pronoun"], |
| 46 | ["PRELAT","PRELAT ", "Attributive Relative Pronoun"], |
| 47 | ["PRELS","PRELS ", "Substitutive Relative Pronoun"], |
| 48 | ["PRF","PRF ", "Reflexive Pronoun"], |
| 49 | ["PROAV","PROAV ", "Pronominal Adverb"], |
| 50 | ["PTKA","PTKA ","Particle with Adjective"], |
| 51 | ["PTKANT","PTKANT ", "Answering Particle"], |
| 52 | ["PTKNEG","PTKNEG ", "Negation Particle"], |
| 53 | ["PTKVZ","PTKVZ ", "Separated Verbal Particle"], |
| 54 | ["PTKZU","PTKZU ", "'zu' Particle"], |
| 55 | ["PWAT","PWAT ", "Attributive Interrogative Pronoun"], |
| 56 | ["PWAV","PWAV ", "Adverbial Interrogative Pronoun"], |
| 57 | ["PWS","PWS ", "Substitutive Interrogative Pronoun"], |
| 58 | ["TRUNC","TRUNC ","Truncated"], |
| 59 | ["VAFIN","VAFIN ", "Auxiliary Finite Verb"], |
Nils Diewald | 023c671 | 2015-05-21 20:12:30 +0000 | [diff] [blame] | 60 | ["VAIMP","VAIMP ", "Auxiliary Finite Imperative Verb"], |
Akron | cff9bac | 2016-01-25 21:39:38 +0100 | [diff] [blame] | 61 | ["VAINF","VAINF ", "Auxiliary Infinite Verb"], |
Nils Diewald | 023c671 | 2015-05-21 20:12:30 +0000 | [diff] [blame] | 62 | ["VAPP","VAPP ", "Auxiliary Perfect Participle"], |
| 63 | ["VMFIN","VMFIN ", "Modal Finite Verb"], |
| 64 | ["VMINF","VMINF ", "Modal Infinite Verb"], |
| 65 | ["VMPP","VMPP ", "Modal Perfect Participle"], |
| 66 | ["VVFIN","VVFIN ","Finite Verb"], |
| 67 | ["VVIMP","VVIMP ", "Finite Imperative Verb"], |
| 68 | ["VVINF","VVINF ", "Infinite Verb"], |
| 69 | ["VVIZU","VVIZU ", "Infinite Verb with 'zu'"], |
| 70 | ["VVPP","VVPP ", "Perfect Participle"], |
| 71 | ["XY", "XY ", "Non-Word"] |
| 72 | ]; |
| 73 | |
Akron | cff9bac | 2016-01-25 21:39:38 +0100 | [diff] [blame] | 74 | |
Akron | 113cc1a | 2016-01-22 21:17:57 +0100 | [diff] [blame] | 75 | // http://www.coli.uni-saarland.de/projects/sfb378/negra-corpus/negra-corpus.html |
| 76 | // http://www.coli.uni-saarland.de/projects/sfb378/negra-corpus/knoten.html |
| 77 | var negraNodes = [ |
| 78 | ["AA", "AA", "superlative phrase with 'am'"], |
| 79 | ["AP","AP", "adjektive phrase"], |
| 80 | ["AVP","AVP", "adverbial phrase"], |
| 81 | ["CAP","CAP", "coordinated adjektive phrase"], |
| 82 | ["CAVP","CAVP", "coordinated adverbial phrase"], |
| 83 | ["CAC","CAC", "coordinated adposition"], |
| 84 | ["CCP","CCP", "coordinated complementiser"], |
| 85 | ["CH","CH", "chunk"], |
| 86 | ["CNP","CNP", "coordinated noun phrase"], |
| 87 | ["CO","CO", "coordination"], |
| 88 | ["CPP","CPP", "coordinated adpositional phrase"], |
| 89 | ["CS","CS", "coordinated sentence"], |
| 90 | ["CVP","CVP", "coordinated verb phrase (non-finite)"], |
| 91 | ["CVZ","CVZ", "coordinated zu-marked infinitive"], |
| 92 | ["DL","DL", "discourse level constituent"], |
| 93 | ["ISU","ISU", "idiosyncratis unit"], |
| 94 | ["MPN","MPN", "multi-word proper noun"], |
| 95 | ["MTA","MTA", "multi-token adjective"], |
| 96 | ["NM","NM", "multi-token number"], |
| 97 | ["NP","NP", "noun phrase"], |
| 98 | ["PP","PP", "adpositional phrase"], |
| 99 | ["QL","QL", "quasi-languag"], |
| 100 | ["ROOT","ROOT", "root node"], |
| 101 | ["S","S", "sentence"], |
| 102 | ["VP","VP", "verb phrase (non-finite)"], |
| 103 | ["VZ","VZ", "zu-marked infinitive"] |
| 104 | ]; |
| 105 | |
| 106 | // http://www.coli.uni-saarland.de/projects/sfb378/negra-corpus/kanten.html |
| 107 | var negraEdges = [ |
| 108 | ["AC","AC","adpositional case marker"], |
| 109 | ["ADC","ADC","adjective component"], |
| 110 | ["AMS","AMS","measure argument of adj"], |
| 111 | ["APP","APP","apposition"], |
| 112 | ["AVC","AVC","adverbial phrase component"], |
| 113 | ["CC","CC","comparative complement"], |
| 114 | ["CD","CD","coordinating conjunction"], |
| 115 | ["CJ","CJ","conjunct"], |
| 116 | ["CM","CM","comparative concjunction"], |
| 117 | ["CP","CP","complementizer"], |
| 118 | ["DA","DA","dative"], |
| 119 | ["DH","DH","discourse-level head"], |
| 120 | ["DM","DM","discourse marker"], |
| 121 | ["GL","GL","prenominal genitive"], |
| 122 | ["GR","GR","postnominal genitive"], |
| 123 | ["HD","HD","head"], |
| 124 | ["JU","JU","junctor"], |
| 125 | ["MC","MC","comitative"], |
| 126 | ["MI","MI","instrumental"], |
| 127 | ["ML","ML","locative"], |
| 128 | ["MNR","MNR","postnominal modifier"], |
| 129 | ["MO","MO","modifier"], |
| 130 | ["MR","MR","rhetorical modifier"], |
| 131 | ["MW","MW","way (directional modifier)"], |
| 132 | ["NG","NG","negation"], |
| 133 | ["NK","NK","noun kernel modifier"], |
| 134 | ["NMC","NMC","numerical component"], |
| 135 | ["OA","OA","accusative object"], |
| 136 | ["OA2","OA2","second accusative object"], |
| 137 | ["OC","OC","clausal object"], |
| 138 | ["OG","OG","genitive object"], |
| 139 | ["PD","PD","predicate"], |
| 140 | ["PG","PG","pseudo-genitive"], |
| 141 | ["PH","PH","placeholder"], |
| 142 | ["PM","PM","morphological particle"], |
| 143 | ["PNC","PNC","proper noun component"], |
| 144 | ["RC","RC","relative clause"], |
| 145 | ["RE","RE","repeated element"], |
| 146 | ["RS","RS","reported speech"], |
| 147 | ["SB","SB","subject"], |
| 148 | ["SBP","SBP","passivised subject (PP)"], |
| 149 | ["SP","SP","subject or predicate"], |
| 150 | ["SVP","SVP","separable verb prefix"], |
| 151 | ["UC","UC","(idiosyncratic) unit component"], |
| 152 | ["VO","VO","vocative"] |
| 153 | ]; |
| 154 | |
Nils Diewald | 023c671 | 2015-05-21 20:12:30 +0000 | [diff] [blame] | 155 | var mateSttsArray = sttsArray.slice(0); |
| 156 | mateSttsArray.push( |
| 157 | ["<root-POS>","<root-POS>","Root Part of Speech"] |
| 158 | ); |
| 159 | |
Akron | b2a0953 | 2016-02-16 19:14:42 +0100 | [diff] [blame] | 160 | var sgbrSttsArray = sttsArray.slice(0); |
Akron | b392385 | 2016-02-01 16:07:59 +0100 | [diff] [blame] | 161 | |
Akron | b2a0953 | 2016-02-16 19:14:42 +0100 | [diff] [blame] | 162 | // Push specific information for Schreibgebrauch |
| 163 | sgbrSttsArray.push( |
| 164 | ["NNE", "NNE", "Normal Nomina with Named Entity"], |
| 165 | ["ADVART","ADVART", "Adverb with Article"], |
| 166 | ["EMOASC","EMOASC", "ASCII emoticon"], |
| 167 | ["EMOIMG","EMOIMG", "Graphic emoticon"], |
| 168 | ["ERRTOK","ERRTOK", "Tokenisation Error"], |
| 169 | ["HST", "HST", "Hashtag"], |
| 170 | ["KOUSPPER","KOUSPPER", "Subordinating Conjunction (with Sentence) with Personal Pronoun"], |
| 171 | ["ONO", "ONO", "Onomatopoeia"], |
| 172 | ["PPERPPER","PPERPPER", "Personal Pronoun with Personal Pronoun"], |
| 173 | ["URL", "URL", "Uniform Resource Locator"], |
| 174 | ["VAPPER", "VAPPER", "Finite Auxiliary Verb with Personal Pronoun"], |
| 175 | ["VMPPER", "VMPPER", "Fintite Modal Verb with Personal Pronoun"], |
| 176 | ["VVPPER", "VVPPER", "Finite Full Verb with Personal Pronoun"], |
| 177 | ["AW", "AW", "Interaction Word"], |
| 178 | ["ADR", "ADR", "Addressing Term"], |
| 179 | ["AWIND", "AWIND", "Punctuation Indicating Addressing Term"], |
| 180 | ["ERRAW","ERRAW", "Part of Erroneously Separated Compound"] |
| 181 | /* |
| 182 | As KorAP currently doesn't support these tags, they could also be ommited |
| 183 | ["_KOMMA", "_KOMMA", "Comma"], |
| 184 | ["_SONST", "_SONST", "Intrasentential Punctuation Mark"], |
| 185 | ["_ENDE", "_ENDE", "Punctuation Mark at the end of the Sentence"] |
| 186 | */ |
| 187 | ); |
| 188 | |
| 189 | // Sort by tag |
| 190 | sgbrSttsArray.sort(function (a,b) { return a[0].localeCompare(b[0]) }); |
Akron | cff9bac | 2016-01-25 21:39:38 +0100 | [diff] [blame] | 191 | |
Akron | 113cc1a | 2016-01-22 21:17:57 +0100 | [diff] [blame] | 192 | define(function () { |
| 193 | var obj = { |
| 194 | "-" : [ |
Akron | cff9bac | 2016-01-25 21:39:38 +0100 | [diff] [blame] | 195 | ["Connexor", "cnx/", "Constituency, Lemma, Morphology, Part-of-Speech, Syntax"], |
| 196 | ["CoreNLP", "corenlp/", "Constituency, Named Entities, Part-of-Speech"], |
| 197 | ["Mate", "mate/", "Lemma, Morphology, Part-of-Speech"], |
| 198 | ["OpenNLP", "opennlp/", "Part-of-Speech"], |
| 199 | ["Schreibgebrauch", "sgbr/", "Lemma, Lemma Variants, Part-of-Speech"], |
| 200 | ["TreeTagger", "tt/", "Lemma, Part-of-Speech"], |
| 201 | ["Xerox Parser", "xip/", "Constituency, Lemma, Part-of-Speech"] |
Akron | 113cc1a | 2016-01-22 21:17:57 +0100 | [diff] [blame] | 202 | ], |
| 203 | "corenlp/" : [ |
| 204 | ["Constituency", "c="], |
| 205 | ["Named Entity", "ne=" , "Combined"], |
| 206 | ["Named Entity", "ne_dewac_175m_600=" , "ne_dewac_175m_600"], |
| 207 | ["Named Entity", "ne_hgc_175m_600=", "ne_hgc_175m_600"], |
| 208 | ["Part-of-Speech", "p="] |
| 209 | ], |
| 210 | "corenlp/ne=" : namedEntities, |
| 211 | "corenlp/ne_dewac_175m_600=" : namedEntities, |
| 212 | "corenlp/ne_hgc_175m_600=" : namedEntities, |
| 213 | "corenlp/p=" : sttsArray, |
| 214 | "corenlp/c=" : negraNodes, |
| 215 | "cnx/" : [ |
| 216 | ["Constituency", "c="], |
| 217 | ["Lemma", "l="], |
| 218 | ["Morphology", "m="], |
| 219 | ["Part-of-Speech", "p="], |
| 220 | ["Syntax", "syn="] |
| 221 | ], |
| 222 | "cnx/c=" : [ |
| 223 | ["np", "np ", "Nominal Phrase"] |
| 224 | ], |
| 225 | // http://www.ids-mannheim.de/cosmas2/projekt/referenz/connexor/morph.html |
| 226 | "cnx/m=" : [ |
| 227 | ["Abbr","Abbr ", "Nouns: Abbreviation"], |
| 228 | ["CMP","CMP ", "Adjective: Comparative"], |
| 229 | ["IMP", "IMP ", "Mood: Imperative"], |
| 230 | ["IND", "IND ", "Mood: Indicative"], |
| 231 | ["INF", "INF ", "Infinitive"], |
| 232 | ["ORD","ORD ", "Numeral: Ordinal"], |
| 233 | ["PAST", "PAST ", "Tense: past"], |
| 234 | ["PCP", "PCP ", "Participle"], |
| 235 | ["PERF", "PERF ", "Perfective Participle"], |
| 236 | ["PL","PL ", "Nouns: Plural"], |
| 237 | ["PRES", "PRES ", "Tense: present"], |
| 238 | ["PROG", "PROG ", "Progressive Participle"], |
| 239 | ["Prop","Prop ", "Nouns: Proper Noun"], |
| 240 | ["SUB", "SUB ", "Mood: Subjunctive"], |
| 241 | ["SUP","SUP ", "Adjective: Superlative"] |
| 242 | ], |
| 243 | // http://www.ids-mannheim.de/cosmas2/projekt/referenz/connexor/morph.html |
| 244 | "cnx/p=" : [ |
| 245 | ["A", "A ", "Adjective"], |
| 246 | ["ADV", "ADV ", "Adverb"], |
| 247 | ["CC", "CC ", "Coordination Marker"], |
| 248 | ["CS", "CS ", "Clause Marker"], |
| 249 | ["DET", "DET ", "Determiner"], |
| 250 | ["INTERJ", "INTERJ ", "Interjection"], |
| 251 | ["N", "N ", "Noun"], |
| 252 | ["NUM", "NUM ", "Numeral"], |
| 253 | ["PREP", "PREP ", "Preposition"], |
| 254 | ["PRON", "PRON ", "Pro-Nominal"], |
| 255 | ["V", "V ", "Verb"] |
| 256 | ], |
| 257 | // http://www.ids-mannheim.de/cosmas2/projekt/referenz/connexor/syntax.html |
| 258 | "cnx/syn=" : [ |
| 259 | ["@ADVL", "@ADVL ", "Adverbial Head"], |
| 260 | ["@AUX", "@AUX ", "Auxiliary Verb"], |
| 261 | ["@CC", "@CC ", "Coordination"] |
| 262 | ["@MAIN", "@MAIN ", "Main Verb"], |
| 263 | ["@NH", "@NH ", "Nominal Head"], |
| 264 | ["@POSTMOD", "@POSTMOD ", "Postmodifier"], |
| 265 | ["@PREMARK", "@PREMARK ", "Preposed Marker"], |
| 266 | ["@PREMOD", "@POSTMOD ", "Premodifier"] |
| 267 | ], |
| 268 | "opennlp/" : [ |
| 269 | ["Part-of-Speech", "p="] |
| 270 | ], |
| 271 | "opennlp/p=" : sttsArray, |
Akron | cff9bac | 2016-01-25 21:39:38 +0100 | [diff] [blame] | 272 | "sgbr/" : [ |
| 273 | ["Lemma", "l="], |
| 274 | ["Lemma Variants", "lv="], |
| 275 | ["Part-of-Speech", "p="] |
| 276 | ], |
Akron | b2a0953 | 2016-02-16 19:14:42 +0100 | [diff] [blame] | 277 | "sgbr/p=" : sgbrSttsArray, |
Akron | 113cc1a | 2016-01-22 21:17:57 +0100 | [diff] [blame] | 278 | "xip/" : [ |
| 279 | ["Constituency", "c="], |
| 280 | // Inactive: ["Dependency", "d="], |
| 281 | ["Lemma", "l="], |
| 282 | ["Part-of-Speech", "p="], |
| 283 | ], |
| 284 | // "xip/c=" : [], |
| 285 | // Inactive: "xip/d=" : [], |
| 286 | // "xip/p=" : [], |
| 287 | "tt/" : [ |
| 288 | ["Lemma", "l="], |
| 289 | ["Part-of-Speech", "p="] |
| 290 | ], |
| 291 | "tt/p=" : sttsArray, |
| 292 | "mate/" : [ |
| 293 | // Inactive: "d" : ["d=", "Dependency"], |
| 294 | ["Lemma", "l="], |
| 295 | ["Morphology", "m="], |
| 296 | ["Part-of-Speech", "p="] |
| 297 | ], |
| 298 | // Inactive: mate/d= |
| 299 | "mate/p=" : mateSttsArray, |
| 300 | "mate/m=" : [ |
| 301 | ["Case", "case:"], |
| 302 | ["Degree", "degree:"], |
| 303 | ["Gender", "gender:"], |
| 304 | ["Mood", "mood:"], |
| 305 | ["Number", "number:"], |
| 306 | ["Person", "person:"], |
| 307 | ["Tense","tense:"], |
| 308 | ["No type", "<no-type> "] |
| 309 | ], |
| 310 | "mate/m=case:" : [ |
| 311 | ["acc", "acc ", "Accusative"], |
| 312 | ["dat","dat ", "Dative"], |
| 313 | ["gen", "gen ","Genitive"], |
| 314 | ["nom","nom ", "Nominative"], |
| 315 | ["*","* ", "Undefined"] |
| 316 | ], |
| 317 | "mate/m=degree:" : [ |
| 318 | ["comp","comp ", "Comparative"], |
| 319 | ["pos","pos ", "Positive"], |
| 320 | ["sup","sup ", "Superative"] |
| 321 | ], |
| 322 | "mate/m=gender:" : [ |
| 323 | ["fem", "fem ", "Feminium"], |
| 324 | ["masc", "masc ", "Masculinum"], |
| 325 | ["neut","neut ", "Neuter"], |
| 326 | ["*","* ","Undefined"] |
| 327 | ], |
| 328 | "mate/m=mood:" : [ |
| 329 | ["imp","imp ", "Imperative"], |
| 330 | ["ind","ind ", "Indicative"], |
| 331 | ["subj","subj ", "Subjunctive"] |
| 332 | ], |
| 333 | "mate/m=number:" : [ |
| 334 | ["pl","pl ","Plural"], |
| 335 | ["sg","sg ","Singular"], |
| 336 | ["*","* ","Undefined"] |
| 337 | ], |
| 338 | "mate/m=person:" : [ |
| 339 | ["1","1 ", "First Person"], |
| 340 | ["2","2 ", "Second Person"], |
| 341 | ["3","3 ", "Third Person"] |
| 342 | ], |
| 343 | "mate/m=tense:" : [ |
| 344 | ["past","past ", "Past"], |
| 345 | ["pres","pres ", "Present"] |
| 346 | ] |
| 347 | }; |
Nils Diewald | 023c671 | 2015-05-21 20:12:30 +0000 | [diff] [blame] | 348 | |
Akron | 113cc1a | 2016-01-22 21:17:57 +0100 | [diff] [blame] | 349 | for (var i in negraNodes) { |
| 350 | obj["corenlp/c=" + negraNodes[i][0] + '-'] = negraEdges; |
| 351 | }; |
| 352 | |
| 353 | return obj; |
Nils Diewald | 023c671 | 2015-05-21 20:12:30 +0000 | [diff] [blame] | 354 | }); |