blob: 529d2b6cbbe79ba725e6fe90819a76f520b83af6 [file] [log] [blame]
Nils Diewald023c6712015-05-21 20:12:30 +00001var 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
9var 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
18var 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 Diewald023c6712015-05-21 20:12:30 +000060 ["VAIMP","VAIMP ", "Auxiliary Finite Imperative Verb"],
Akroncff9bac2016-01-25 21:39:38 +010061 ["VAINF","VAINF ", "Auxiliary Infinite Verb"],
Nils Diewald023c6712015-05-21 20:12:30 +000062 ["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
Akroncff9bac2016-01-25 21:39:38 +010074
Akron113cc1a2016-01-22 21:17:57 +010075// 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
77var 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
107var 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 Diewald023c6712015-05-21 20:12:30 +0000155var mateSttsArray = sttsArray.slice(0);
156mateSttsArray.push(
157 ["<root-POS>","<root-POS>","Root Part of Speech"]
158);
159
Akroncff9bac2016-01-25 21:39:38 +0100160var sgbSttsArray = sttsArray.slice(0);
161sgbSttsArray.splice(17,0, ["NNE", "NNE", "Normal Nomina with Named Entity"]);
Akronb3923852016-02-01 16:07:59 +0100162/* As KorAP currently doesn't support these tags, they are not part of the set
Akroncff9bac2016-01-25 21:39:38 +0100163sgbSttsArray.push(
164 ["_KOMMA", "_KOMMA", "Comma"],
165 ["_SONST", "_SONST", "Intrasentential Punctuation Mark"],
166 ["_ENDE", "_ENDE", "Punctuation Mark at the end of the Sentence"]
167);
Akronb3923852016-02-01 16:07:59 +0100168*/
169/*
170"ADR", // Adressierung ???
171"ADVART", "Adverb with Article"
172"AW", // Aktionswort ???
173"AWIND", // Aktionswort-Indikator ???
174"EMOASC", "Emoticon ('ASCII' type)",
175"EMOIMG", "Emoticon (\'image' type )",
176"ERRAW", // falsch abgetrennter Wortteil ???
177"ERRTOK", "Tokenisation Error"
178"HST", "Hashtag"
179"KOUSPPER", "Subordinating Conjunction (with Sentence) with Personal Pronoun"
180"ONO", // Onomatopoetikon ???
181"PPERPPER", "Personal Pronoun with Personal Pronoun"
182"URL", "Uniform Resource Locator"
183"VAPPER", "Auxiliary Finite Verb with Personal Pronoun"
184"VMPPER", "Modal Fintite Verb with Personal Pronoun"
185"VVPPER", "Finite Verb with Personal Pronoun"
186*/
187
Akroncff9bac2016-01-25 21:39:38 +0100188
Akron113cc1a2016-01-22 21:17:57 +0100189define(function () {
190 var obj = {
191 "-" : [
Akroncff9bac2016-01-25 21:39:38 +0100192 ["Connexor", "cnx/", "Constituency, Lemma, Morphology, Part-of-Speech, Syntax"],
193 ["CoreNLP", "corenlp/", "Constituency, Named Entities, Part-of-Speech"],
194 ["Mate", "mate/", "Lemma, Morphology, Part-of-Speech"],
195 ["OpenNLP", "opennlp/", "Part-of-Speech"],
196 ["Schreibgebrauch", "sgbr/", "Lemma, Lemma Variants, Part-of-Speech"],
197 ["TreeTagger", "tt/", "Lemma, Part-of-Speech"],
198 ["Xerox Parser", "xip/", "Constituency, Lemma, Part-of-Speech"]
Akron113cc1a2016-01-22 21:17:57 +0100199 ],
200 "corenlp/" : [
201 ["Constituency", "c="],
202 ["Named Entity", "ne=" , "Combined"],
203 ["Named Entity", "ne_dewac_175m_600=" , "ne_dewac_175m_600"],
204 ["Named Entity", "ne_hgc_175m_600=", "ne_hgc_175m_600"],
205 ["Part-of-Speech", "p="]
206 ],
207 "corenlp/ne=" : namedEntities,
208 "corenlp/ne_dewac_175m_600=" : namedEntities,
209 "corenlp/ne_hgc_175m_600=" : namedEntities,
210 "corenlp/p=" : sttsArray,
211 "corenlp/c=" : negraNodes,
212 "cnx/" : [
213 ["Constituency", "c="],
214 ["Lemma", "l="],
215 ["Morphology", "m="],
216 ["Part-of-Speech", "p="],
217 ["Syntax", "syn="]
218 ],
219 "cnx/c=" : [
220 ["np", "np ", "Nominal Phrase"]
221 ],
222 // http://www.ids-mannheim.de/cosmas2/projekt/referenz/connexor/morph.html
223 "cnx/m=" : [
224 ["Abbr","Abbr ", "Nouns: Abbreviation"],
225 ["CMP","CMP ", "Adjective: Comparative"],
226 ["IMP", "IMP ", "Mood: Imperative"],
227 ["IND", "IND ", "Mood: Indicative"],
228 ["INF", "INF ", "Infinitive"],
229 ["ORD","ORD ", "Numeral: Ordinal"],
230 ["PAST", "PAST ", "Tense: past"],
231 ["PCP", "PCP ", "Participle"],
232 ["PERF", "PERF ", "Perfective Participle"],
233 ["PL","PL ", "Nouns: Plural"],
234 ["PRES", "PRES ", "Tense: present"],
235 ["PROG", "PROG ", "Progressive Participle"],
236 ["Prop","Prop ", "Nouns: Proper Noun"],
237 ["SUB", "SUB ", "Mood: Subjunctive"],
238 ["SUP","SUP ", "Adjective: Superlative"]
239 ],
240 // http://www.ids-mannheim.de/cosmas2/projekt/referenz/connexor/morph.html
241 "cnx/p=" : [
242 ["A", "A ", "Adjective"],
243 ["ADV", "ADV ", "Adverb"],
244 ["CC", "CC ", "Coordination Marker"],
245 ["CS", "CS ", "Clause Marker"],
246 ["DET", "DET ", "Determiner"],
247 ["INTERJ", "INTERJ ", "Interjection"],
248 ["N", "N ", "Noun"],
249 ["NUM", "NUM ", "Numeral"],
250 ["PREP", "PREP ", "Preposition"],
251 ["PRON", "PRON ", "Pro-Nominal"],
252 ["V", "V ", "Verb"]
253 ],
254 // http://www.ids-mannheim.de/cosmas2/projekt/referenz/connexor/syntax.html
255 "cnx/syn=" : [
256 ["@ADVL", "@ADVL ", "Adverbial Head"],
257 ["@AUX", "@AUX ", "Auxiliary Verb"],
258 ["@CC", "@CC ", "Coordination"]
259 ["@MAIN", "@MAIN ", "Main Verb"],
260 ["@NH", "@NH ", "Nominal Head"],
261 ["@POSTMOD", "@POSTMOD ", "Postmodifier"],
262 ["@PREMARK", "@PREMARK ", "Preposed Marker"],
263 ["@PREMOD", "@POSTMOD ", "Premodifier"]
264 ],
265 "opennlp/" : [
266 ["Part-of-Speech", "p="]
267 ],
268 "opennlp/p=" : sttsArray,
Akroncff9bac2016-01-25 21:39:38 +0100269 "sgbr/" : [
270 ["Lemma", "l="],
271 ["Lemma Variants", "lv="],
272 ["Part-of-Speech", "p="]
273 ],
274 "sgbr/p=" : sgbSttsArray,
Akron113cc1a2016-01-22 21:17:57 +0100275 "xip/" : [
276 ["Constituency", "c="],
277 // Inactive: ["Dependency", "d="],
278 ["Lemma", "l="],
279 ["Part-of-Speech", "p="],
280 ],
281 // "xip/c=" : [],
282 // Inactive: "xip/d=" : [],
283 // "xip/p=" : [],
284 "tt/" : [
285 ["Lemma", "l="],
286 ["Part-of-Speech", "p="]
287 ],
288 "tt/p=" : sttsArray,
289 "mate/" : [
290 // Inactive: "d" : ["d=", "Dependency"],
291 ["Lemma", "l="],
292 ["Morphology", "m="],
293 ["Part-of-Speech", "p="]
294 ],
295 // Inactive: mate/d=
296 "mate/p=" : mateSttsArray,
297 "mate/m=" : [
298 ["Case", "case:"],
299 ["Degree", "degree:"],
300 ["Gender", "gender:"],
301 ["Mood", "mood:"],
302 ["Number", "number:"],
303 ["Person", "person:"],
304 ["Tense","tense:"],
305 ["No type", "<no-type> "]
306 ],
307 "mate/m=case:" : [
308 ["acc", "acc ", "Accusative"],
309 ["dat","dat ", "Dative"],
310 ["gen", "gen ","Genitive"],
311 ["nom","nom ", "Nominative"],
312 ["*","* ", "Undefined"]
313 ],
314 "mate/m=degree:" : [
315 ["comp","comp ", "Comparative"],
316 ["pos","pos ", "Positive"],
317 ["sup","sup ", "Superative"]
318 ],
319 "mate/m=gender:" : [
320 ["fem", "fem ", "Feminium"],
321 ["masc", "masc ", "Masculinum"],
322 ["neut","neut ", "Neuter"],
323 ["*","* ","Undefined"]
324 ],
325 "mate/m=mood:" : [
326 ["imp","imp ", "Imperative"],
327 ["ind","ind ", "Indicative"],
328 ["subj","subj ", "Subjunctive"]
329 ],
330 "mate/m=number:" : [
331 ["pl","pl ","Plural"],
332 ["sg","sg ","Singular"],
333 ["*","* ","Undefined"]
334 ],
335 "mate/m=person:" : [
336 ["1","1 ", "First Person"],
337 ["2","2 ", "Second Person"],
338 ["3","3 ", "Third Person"]
339 ],
340 "mate/m=tense:" : [
341 ["past","past ", "Past"],
342 ["pres","pres ", "Present"]
343 ]
344 };
Nils Diewald023c6712015-05-21 20:12:30 +0000345
Akron113cc1a2016-01-22 21:17:57 +0100346 for (var i in negraNodes) {
347 obj["corenlp/c=" + negraNodes[i][0] + '-'] = negraEdges;
348 };
349
350 return obj;
Nils Diewald023c6712015-05-21 20:12:30 +0000351});