diff --git a/spacy/lang/nb/tag_map.py b/spacy/lang/nb/tag_map.py index 28220c471..c81a3074c 100644 --- a/spacy/lang/nb/tag_map.py +++ b/spacy/lang/nb/tag_map.py @@ -6,34 +6,238 @@ from __future__ import unicode_literals from ...symbols import POS, PUNCT, ADJ, CONJ, CCONJ, SCONJ, SYM, NUM, DET, ADV, ADP, X, VERB from ...symbols import NOUN, PROPN, PART, INTJ, SPACE, PRON, AUX - TAG_MAP = { - "$(": {POS: PUNCT, "PunctType": "PUNCT"}, - "$)": {POS: PUNCT, "PunctType": "PUNCT"}, - # PUNCT - # PUNCT - "$,": {POS: PUNCT, "PunctType": "PUNCT"}, - "$.": {POS: PUNCT, "PunctType": "PUNCT"}, - "$\"": {POS: PUNCT, "PunctType": "PUNCT"}, - "$-": {POS: PUNCT, "PunctType": "PUNCT"}, - - 'NOUN': {POS: NOUN}, - 'PROPN': {POS: PROPN}, - 'VERB': {POS: VERB}, - 'PUNCT': {POS: PUNCT}, - 'ADJ': {POS: ADJ}, - 'ADP': {POS: ADP}, - 'PART': {POS: PART}, - 'DET': {POS: DET}, - 'AUX': {POS: AUX}, - 'PRON': {POS: PRON}, - 'CCONJ': {POS: CCONJ}, - 'NUM': {POS: NUM}, - 'ADV': {POS: ADV}, - 'SCONJ': {POS: SCONJ}, - 'SYM': {POS: SYM}, - 'X': {POS: X}, - 'INTJ': {POS: INTJ}, + 'NOUN__Definite=Ind|Gender=Neut|Number=Sing': {'morph': 'Definite=Ind|Gender=Neut|Number=Sing', POS: NOUN}, + 'CCONJ___': {'morph': '_', POS: CCONJ}, + 'NOUN__Definite=Ind|Gender=Masc|Number=Sing': {'morph': 'Definite=Ind|Gender=Masc|Number=Sing', POS: NOUN}, + 'ADP___': {'morph': '_', POS: ADP}, + 'NOUN__Definite=Def|Gender=Masc|Number=Sing': {'morph': 'Definite=Def|Gender=Masc|Number=Sing', POS: NOUN}, + 'NOUN__Definite=Ind|Gender=Neut|Number=Plur': {'morph': 'Definite=Ind|Gender=Neut|Number=Plur', POS: NOUN}, + 'PUNCT___': {'morph': '_', POS: PUNCT}, + 'VERB__Mood=Ind|Tense=Past|VerbForm=Fin': {'morph': 'Mood=Ind|Tense=Past|VerbForm=Fin', POS: VERB}, + 'DET__Gender=Masc|Number=Sing|PronType=Dem': {'morph': 'Gender=Masc|Number=Sing|PronType=Dem', POS: DET}, + 'ADJ__Definite=Def|Degree=Pos|Number=Sing': {'morph': 'Definite=Def|Degree=Pos|Number=Sing', POS: ADJ}, + 'PROPN___': {'morph': '_', POS: PROPN}, + 'X___': {'morph': '_', POS: X}, + 'VERB__Mood=Ind|Tense=Pres|VerbForm=Fin': {'morph': 'Mood=Ind|Tense=Pres|VerbForm=Fin', POS: VERB}, + 'NOUN__Definite=Def|Gender=Neut|Number=Sing': {'morph': 'Definite=Def|Gender=Neut|Number=Sing', POS: NOUN}, + 'PRON__PronType=Rel': {'morph': 'PronType=Rel', POS: PRON}, + 'AUX__Mood=Ind|Tense=Pres|VerbForm=Fin': {'morph': 'Mood=Ind|Tense=Pres|VerbForm=Fin', POS: AUX}, + 'ADJ__Definite=Ind|Gender=Neut|Number=Sing|VerbForm=Part': {'morph': 'Definite=Ind|Gender=Neut|Number=Sing|VerbForm=Part', POS: ADJ}, + 'ADJ__Definite=Ind|Degree=Pos|Number=Sing': {'morph': 'Definite=Ind|Degree=Pos|Number=Sing', POS: ADJ}, + 'NOUN__Definite=Ind|Gender=Fem|Number=Sing': {'morph': 'Definite=Ind|Gender=Fem|Number=Sing', POS: NOUN}, + 'ADJ__Number=Plur|VerbForm=Part': {'morph': 'Number=Plur|VerbForm=Part', POS: ADJ}, + 'NOUN__Definite=Ind|Gender=Fem|Number=Plur': {'morph': 'Definite=Ind|Gender=Fem|Number=Plur', POS: NOUN}, + 'ADV___': {'morph': '_', POS: ADV}, + 'PRON__Gender=Neut|Number=Sing|Person=3|PronType=Prs': {'morph': 'Gender=Neut|Number=Sing|Person=3|PronType=Prs', POS: PRON}, + 'ADJ__Definite=Ind|Number=Sing|VerbForm=Part': {'morph': 'Definite=Ind|Number=Sing|VerbForm=Part', POS: ADJ}, + 'VERB__VerbForm=Part': {'morph': 'VerbForm=Part', POS: VERB}, + 'NOUN__Definite=Ind|Gender=Masc|Number=Plur': {'morph': 'Definite=Ind|Gender=Masc|Number=Plur', POS: NOUN}, + 'ADJ__Definite=Ind|Degree=Pos|Gender=Neut|Number=Sing': {'morph': 'Definite=Ind|Degree=Pos|Gender=Neut|Number=Sing', POS: ADJ}, + 'ADJ__Degree=Pos|Number=Plur': {'morph': 'Degree=Pos|Number=Plur', POS: ADJ}, + 'NUM__Number=Plur|NumType=Card': {'morph': 'Number=Plur|NumType=Card', POS: NUM}, + 'NOUN__Definite=Def|Gender=Masc|Number=Plur': {'morph': 'Definite=Def|Gender=Masc|Number=Plur', POS: NOUN}, + 'PRON__Case=Acc|PronType=Prs|Reflex=Yes': {'morph': 'Case=Acc|PronType=Prs|Reflex=Yes', POS: PRON}, + 'NOUN__Case=Gen|Definite=Ind|Gender=Neut|Number=Sing': {'morph': 'Case=Gen|Definite=Ind|Gender=Neut|Number=Sing', POS: NOUN}, + 'PART___': {'morph': '_', POS: PART}, + 'VERB__VerbForm=Inf': {'morph': 'VerbForm=Inf', POS: VERB}, + 'PRON__Case=Nom|Number=Plur|Person=3|PronType=Prs': {'morph': 'Case=Nom|Number=Plur|Person=3|PronType=Prs', POS: PRON}, + 'AUX__Mood=Ind|Tense=Past|VerbForm=Fin': {'morph': 'Mood=Ind|Tense=Past|VerbForm=Fin', POS: AUX}, + 'PROPN__Gender=Fem': {'morph': 'Gender=Fem', POS: PROPN}, + 'NOUN___': {'morph': '_', POS: NOUN}, + 'PROPN__Gender=Masc': {'morph': 'Gender=Masc', POS: PROPN}, + 'DET__Gender=Neut|Number=Sing|PronType=Dem': {'morph': 'Gender=Neut|Number=Sing|PronType=Dem', POS: DET}, + 'DET__Gender=Masc|Number=Sing|PronType=Art': {'morph': 'Gender=Masc|Number=Sing|PronType=Art', POS: DET}, + 'NOUN__Case=Gen|Definite=Def|Gender=Masc|Number=Sing': {'morph': 'Case=Gen|Definite=Def|Gender=Masc|Number=Sing', POS: NOUN}, + 'PROPN__Abbr=Yes': {'morph': 'Abbr=Yes', POS: PROPN}, + 'ADV__Polarity=Neg': {'morph': 'Polarity=Neg', POS: ADV}, + 'SCONJ___': {'morph': '_', POS: SCONJ}, + 'DET__Number=Plur|Poss=Yes|PronType=Prs': {'morph': 'Number=Plur|Poss=Yes|PronType=Prs', POS: DET}, + 'NOUN__Case=Gen|Definite=Ind|Gender=Neut|Number=Plur': {'morph': 'Case=Gen|Definite=Ind|Gender=Neut|Number=Plur', POS: NOUN}, + 'PROPN__Case=Gen': {'morph': 'Case=Gen', POS: PROPN}, + 'DET__Gender=Fem|Number=Sing|PronType=Dem': {'morph': 'Gender=Fem|Number=Sing|PronType=Dem', POS: DET}, + 'DET__Gender=Masc|Number=Sing|Poss=Yes|PronType=Prs': {'morph': 'Gender=Masc|Number=Sing|Poss=Yes|PronType=Prs', POS: DET}, + 'ADJ__Definite=Def|Degree=Sup': {'morph': 'Definite=Def|Degree=Sup', POS: ADJ}, + 'PROPN__Case=Gen|Gender=Fem': {'morph': 'Case=Gen|Gender=Fem', POS: PROPN}, + 'DET__Number=Plur|PronType=Dem': {'morph': 'Number=Plur|PronType=Dem', POS: DET}, + 'NOUN__Case=Gen|Definite=Def|Gender=Neut|Number=Sing': {'morph': 'Case=Gen|Definite=Def|Gender=Neut|Number=Sing', POS: NOUN}, + 'ADJ__Definite=Ind|Degree=Sup': {'morph': 'Definite=Ind|Degree=Sup', POS: ADJ}, + 'NOUN__Definite=Def|Gender=Fem|Number=Plur': {'morph': 'Definite=Def|Gender=Fem|Number=Plur', POS: NOUN}, + 'PROPN__Gender=Neut': {'morph': 'Gender=Neut', POS: PROPN}, + 'DET__Number=Plur|PronType=Int': {'morph': 'Number=Plur|PronType=Int', POS: DET}, + 'NOUN__Definite=Def|Gender=Neut|Number=Plur': {'morph': 'Definite=Def|Gender=Neut|Number=Plur', POS: NOUN}, + 'DET__Definite=Def|PronType=Dem': {'morph': 'Definite=Def|PronType=Dem', POS: DET}, + 'DET__Gender=Neut|Number=Sing|PronType=Art': {'morph': 'Gender=Neut|Number=Sing|PronType=Art', POS: DET}, + 'VERB__Mood=Ind|Tense=Pres|VerbForm=Fin|Voice=Pass': {'morph': 'Mood=Ind|Tense=Pres|VerbForm=Fin|Voice=Pass', POS: VERB}, + 'PROPN__Abbr=Yes|Case=Gen': {'morph': 'Abbr=Yes|Case=Gen', POS: PROPN}, + 'PRON__Animacy=Hum|Case=Nom|Gender=Masc|Number=Sing|Person=3|PronType=Prs': {'morph': 'Animacy=Hum|Case=Nom|Gender=Masc|Number=Sing|Person=3|PronType=Prs', POS: PRON}, + 'ADJ__Degree=Cmp': {'morph': 'Degree=Cmp', POS: ADJ}, + 'ADJ__VerbForm=Part': {'morph': 'VerbForm=Part', POS: ADJ}, + 'DET__Gender=Neut|Number=Sing|Poss=Yes|PronType=Prs': {'morph': 'Gender=Neut|Number=Sing|Poss=Yes|PronType=Prs', POS: DET}, + 'ADP__Abbr=Yes': {'morph': 'Abbr=Yes', POS: ADP}, + 'DET__Definite=Ind|Gender=Neut|Number=Sing|PronType=Prs': {'morph': 'Definite=Ind|Gender=Neut|Number=Sing|PronType=Prs', POS: DET}, + 'NOUN__Case=Gen|Definite=Def|Gender=Neut|Number=Plur': {'morph': 'Case=Gen|Definite=Def|Gender=Neut|Number=Plur', POS: NOUN}, + 'AUX__VerbForm=Part': {'morph': 'VerbForm=Part', POS: AUX}, + 'PRON__PronType=Int': {'morph': 'PronType=Int', POS: PRON}, + 'DET__Gender=Fem|Number=Sing|Poss=Yes|PronType=Prs': {'morph': 'Gender=Fem|Number=Sing|Poss=Yes|PronType=Prs', POS: DET}, + 'PRON__Number=Plur|Person=3|PronType=Ind,Prs': {'morph': 'Number=Plur|Person=3|PronType=Ind,Prs', POS: PRON}, + 'DET__Number=Plur|PronType=Ind': {'morph': 'Number=Plur|PronType=Ind', POS: DET}, + 'ADJ__Degree=Pos': {'morph': 'Degree=Pos', POS: ADJ}, + 'PRON__Animacy=Hum|Case=Nom|Number=Plur|Person=1|PronType=Prs': {'morph': 'Animacy=Hum|Case=Nom|Number=Plur|Person=1|PronType=Prs', POS: PRON}, + 'VERB__VerbForm=Inf|Voice=Pass': {'morph': 'VerbForm=Inf|Voice=Pass', POS: VERB}, + 'DET__Definite=Ind|Gender=Fem|Number=Sing|PronType=Dem': {'morph': 'Definite=Ind|Gender=Fem|Number=Sing|PronType=Dem', POS: DET}, + 'DET__Gender=Neut|Number=Sing|PronType=Ind': {'morph': 'Gender=Neut|Number=Sing|PronType=Ind', POS: DET}, + 'PRON__Animacy=Hum|Case=Acc|Gender=Masc|Number=Sing|Person=3|PronType=Prs': {'morph': 'Animacy=Hum|Case=Acc|Gender=Masc|Number=Sing|Person=3|PronType=Prs', POS: PRON}, + 'PRON__Animacy=Hum|Case=Nom|Number=Sing|Person=1|PronType=Prs': {'morph': 'Animacy=Hum|Case=Nom|Number=Sing|Person=1|PronType=Prs', POS: PRON}, + 'DET__Number=Plur|Polarity=Neg|PronType=Neg': {'morph': 'Number=Plur|Polarity=Neg|PronType=Neg', POS: DET}, + 'NUM__NumType=Card': {'morph': 'NumType=Card', POS: NUM}, + 'DET__Gender=Masc|Number=Sing|PronType=Ind': {'morph': 'Gender=Masc|Number=Sing|PronType=Ind', POS: DET}, + 'DET__PronType=Prs': {'morph': 'PronType=Prs', POS: DET}, + 'DET__Gender=Fem|Number=Sing|PronType=Ind': {'morph': 'Gender=Fem|Number=Sing|PronType=Ind', POS: DET}, + 'PROPN__Case=Gen|Gender=Neut': {'morph': 'Case=Gen|Gender=Neut', POS: PROPN}, + 'DET__Gender=Masc|Number=Sing|Polarity=Neg|PronType=Neg': {'morph': 'Gender=Masc|Number=Sing|Polarity=Neg|PronType=Neg', POS: DET}, + 'ADJ__Definite=Def|Number=Sing|VerbForm=Part': {'morph': 'Definite=Def|Number=Sing|VerbForm=Part', POS: ADJ}, + 'PRON__Gender=Fem,Masc|Number=Sing|Person=3|PronType=Prs': {'morph': 'Gender=Fem,Masc|Number=Sing|Person=3|PronType=Prs', POS: PRON}, + 'AUX__VerbForm=Inf': {'morph': 'VerbForm=Inf', POS: AUX}, + 'PRON__Case=Acc|Number=Plur|Person=3|PronType=Prs': {'morph': 'Case=Acc|Number=Plur|Person=3|PronType=Prs', POS: PRON}, + 'ADJ__Case=Gen|Degree=Pos|Number=Plur': {'morph': 'Case=Gen|Degree=Pos|Number=Plur', POS: ADJ}, + 'DET__Number=Plur|PronType=Tot': {'morph': 'Number=Plur|PronType=Tot', POS: DET}, + 'DET__Case=Gen|Gender=Masc|Number=Sing|PronType=Dem': {'morph': 'Case=Gen|Gender=Masc|Number=Sing|PronType=Dem', POS: DET}, + 'DET__Number=Plur|PronType=Prs': {'morph': 'Number=Plur|PronType=Prs', POS: DET}, + 'SYM___': {'morph': '_', POS: SYM}, + 'NUM__Gender=Neut|Number=Sing|NumType=Card': {'morph': 'Gender=Neut|Number=Sing|NumType=Card', POS: NUM}, + 'PRON__Animacy=Hum|Case=Nom|Number=Sing|PronType=Prs': {'morph': 'Animacy=Hum|Case=Nom|Number=Sing|PronType=Prs', POS: PRON}, + 'DET__Definite=Ind|Gender=Masc|Number=Sing|PronType=Prs': {'morph': 'Definite=Ind|Gender=Masc|Number=Sing|PronType=Prs', POS: DET}, + 'NOUN__Case=Gen|Definite=Ind|Gender=Masc|Number=Sing': {'morph': 'Case=Gen|Definite=Ind|Gender=Masc|Number=Sing', POS: NOUN}, + 'ADV__Abbr=Yes': {'morph': 'Abbr=Yes', POS: ADV}, + 'DET__Definite=Ind|Gender=Neut|Number=Sing|PronType=Dem': {'morph': 'Definite=Ind|Gender=Neut|Number=Sing|PronType=Dem', POS: DET}, + 'DET__Gender=Masc|Number=Sing|PronType=Tot': {'morph': 'Gender=Masc|Number=Sing|PronType=Tot', POS: DET}, + 'DET__Definite=Def|PronType=Prs': {'morph': 'Definite=Def|PronType=Prs', POS: DET}, + 'PRON__Animacy=Hum|Case=Nom|Gender=Fem|Number=Sing|Person=3|PronType=Prs': {'morph': 'Animacy=Hum|Case=Nom|Gender=Fem|Number=Sing|Person=3|PronType=Prs', POS: PRON}, + 'NOUN__Gender=Neut': {'morph': 'Gender=Neut', POS: NOUN}, + 'DET__Gender=Neut|Number=Sing|PronType=Int': {'morph': 'Gender=Neut|Number=Sing|PronType=Int', POS: DET}, + 'NUM__Definite=Def|NumType=Card': {'morph': 'Definite=Def|NumType=Card', POS: NUM}, + 'VERB__Mood=Imp|VerbForm=Fin': {'morph': 'Mood=Imp|VerbForm=Fin', POS: VERB}, + 'NOUN__Definite=Ind|Number=Plur': {'morph': 'Definite=Ind|Number=Plur', POS: NOUN}, + 'DET__Gender=Neut|Number=Sing|PronType=Tot': {'morph': 'Gender=Neut|Number=Sing|PronType=Tot', POS: DET}, + 'DET__Gender=Fem|Number=Sing|PronType=Tot': {'morph': 'Gender=Fem|Number=Sing|PronType=Tot', POS: DET}, + 'PRON__Animacy=Hum|Case=Acc|Number=Plur|Person=1|PronType=Prs': {'morph': 'Animacy=Hum|Case=Acc|Number=Plur|Person=1|PronType=Prs', POS: PRON}, + 'PRON__Gender=Fem,Masc|Number=Sing|Person=3|Polarity=Neg|PronType=Neg,Prs': {'morph': 'Gender=Fem,Masc|Number=Sing|Person=3|Polarity=Neg|PronType=Neg,Prs', POS: PRON}, + 'PRON__Number=Plur|Person=3|Polarity=Neg|PronType=Neg,Prs': {'morph': 'Number=Plur|Person=3|Polarity=Neg|PronType=Neg,Prs', POS: PRON}, + 'NUM__Definite=Def|Number=Sing|NumType=Card': {'morph': 'Definite=Def|Number=Sing|NumType=Card', POS: NUM}, + 'NUM__Gender=Masc|Number=Sing|NumType=Card': {'morph': 'Gender=Masc|Number=Sing|NumType=Card', POS: NUM}, + 'DET__Definite=Ind|Gender=Masc|Number=Sing|PronType=Dem': {'morph': 'Definite=Ind|Gender=Masc|Number=Sing|PronType=Dem', POS: DET}, + 'NOUN__Case=Gen|Definite=Def|Gender=Fem|Number=Plur': {'morph': 'Case=Gen|Definite=Def|Gender=Fem|Number=Plur', POS: NOUN}, + 'DET__Case=Gen|Gender=Neut|Number=Sing|PronType=Dem': {'morph': 'Case=Gen|Gender=Neut|Number=Sing|PronType=Dem', POS: DET}, + 'PRON__Animacy=Hum|Number=Sing|PronType=Art,Prs': {'morph': 'Animacy=Hum|Number=Sing|PronType=Art,Prs', POS: PRON}, + 'AUX__Mood=Imp|VerbForm=Fin': {'morph': 'Mood=Imp|VerbForm=Fin', POS: AUX}, + 'PRON__Number=Plur|Person=3|PronType=Prs,Tot': {'morph': 'Number=Plur|Person=3|PronType=Prs,Tot', POS: PRON}, + 'ADJ__Number=Plur': {'morph': 'Number=Plur', POS: ADJ}, + 'NOUN__Gender=Masc': {'morph': 'Gender=Masc', POS: NOUN}, + 'NOUN__Abbr=Yes': {'morph': 'Abbr=Yes', POS: NOUN}, + 'NOUN__Case=Gen|Definite=Ind|Gender=Masc|Number=Plur': {'morph': 'Case=Gen|Definite=Ind|Gender=Masc|Number=Plur', POS: NOUN}, + 'PRON__Gender=Neut|Number=Sing|Person=3|PronType=Ind,Prs': {'morph': 'Gender=Neut|Number=Sing|Person=3|PronType=Ind,Prs', POS: PRON}, + 'INTJ___': {'morph': '_', POS: INTJ}, + 'PRON__Animacy=Hum|Case=Nom|Number=Sing|Person=2|PronType=Prs': {'morph': 'Animacy=Hum|Case=Nom|Number=Sing|Person=2|PronType=Prs', POS: PRON}, + 'PRON__Animacy=Hum|Case=Acc|Number=Sing|Person=1|PronType=Prs': {'morph': 'Animacy=Hum|Case=Acc|Number=Sing|Person=1|PronType=Prs', POS: PRON}, + 'NOUN__Case=Gen|Definite=Def|Gender=Masc|Number=Plur': {'morph': 'Case=Gen|Definite=Def|Gender=Masc|Number=Plur', POS: NOUN}, + 'ADJ___': {'morph': '_', POS: ADJ}, + 'PRON__Animacy=Hum|Case=Acc|Gender=Fem|Number=Sing|Person=3|PronType=Prs': {'morph': 'Animacy=Hum|Case=Acc|Gender=Fem|Number=Sing|Person=3|PronType=Prs', POS: PRON}, + 'PRON__Animacy=Hum|Case=Acc|Number=Sing|Person=2|PronType=Prs': {'morph': 'Animacy=Hum|Case=Acc|Number=Sing|Person=2|PronType=Prs', POS: PRON}, + 'NOUN__Definite=Def|Gender=Fem|Number=Sing': {'morph': 'Definite=Def|Gender=Fem|Number=Sing', POS: NOUN}, + 'PRON__Number=Sing|Polarity=Neg|PronType=Neg': {'morph': 'Number=Sing|Polarity=Neg|PronType=Neg', POS: PRON}, + 'NOUN__Case=Gen': {'morph': 'Case=Gen', POS: NOUN}, + 'ADJ__Definite=Ind|Number=Sing': {'morph': 'Definite=Ind|Number=Sing', POS: ADJ}, + 'PROPN__Case=Gen|Gender=Masc': {'morph': 'Case=Gen|Gender=Masc', POS: PROPN}, + 'PRON__Animacy=Hum|Number=Plur|PronType=Rcp': {'morph': 'Animacy=Hum|Number=Plur|PronType=Rcp', POS: PRON}, + 'NOUN__Case=Gen|Definite=Ind|Gender=Fem|Number=Sing': {'morph': 'Case=Gen|Definite=Ind|Gender=Fem|Number=Sing', POS: NOUN}, + 'PRON__Number=Plur|Person=3|PronType=Prs': {'morph': 'Number=Plur|Person=3|PronType=Prs', POS: PRON}, + 'PRON__Gender=Fem,Masc|Number=Sing|Person=3|PronType=Ind,Prs': {'morph': 'Gender=Fem,Masc|Number=Sing|Person=3|PronType=Ind,Prs', POS: PRON}, + 'DET__Definite=Ind|Gender=Fem|Number=Sing|PronType=Prs': {'morph': 'Definite=Ind|Gender=Fem|Number=Sing|PronType=Prs', POS: DET}, + 'NOUN__Case=Gen|Definite=Def|Gender=Fem|Number=Sing': {'morph': 'Case=Gen|Definite=Def|Gender=Fem|Number=Sing', POS: NOUN}, + 'DET__Gender=Fem|Number=Sing|PronType=Art': {'morph': 'Gender=Fem|Number=Sing|PronType=Art', POS: DET}, + 'ADJ__Case=Gen|Definite=Def|Degree=Pos|Number=Sing': {'morph': 'Case=Gen|Definite=Def|Degree=Pos|Number=Sing', POS: ADJ}, + 'DET__Gender=Masc|Number=Sing|PronType=Int': {'morph': 'Gender=Masc|Number=Sing|PronType=Int', POS: DET}, + 'NUM__Number=Sing|NumType=Card': {'morph': 'Number=Sing|NumType=Card', POS: NUM}, + 'PRON__Animacy=Hum|Case=Acc|Number=Plur|Person=2|PronType=Prs': {'morph': 'Animacy=Hum|Case=Acc|Number=Plur|Person=2|PronType=Prs', POS: PRON}, + 'PRON__Animacy=Hum|Case=Nom|Number=Plur|Person=2|PronType=Prs': {'morph': 'Animacy=Hum|Case=Nom|Number=Plur|Person=2|PronType=Prs', POS: PRON}, + 'ADJ__Case=Gen|Definite=Ind|Degree=Pos|Gender=Neut|Number=Sing': {'morph': 'Case=Gen|Definite=Ind|Degree=Pos|Gender=Neut|Number=Sing', POS: ADJ}, + 'ADJ__Degree=Sup': {'morph': 'Degree=Sup', POS: ADJ}, + 'PRON__Animacy=Hum|PronType=Int': {'morph': 'Animacy=Hum|PronType=Int', POS: PRON}, + 'DET__PronType=Ind': {'morph': 'PronType=Ind', POS: DET}, + 'DET__Definite=Def|Number=Sing|PronType=Dem': {'morph': 'Definite=Def|Number=Sing|PronType=Dem', POS: DET}, + 'NOUN__Gender=Fem': {'morph': 'Gender=Fem', POS: NOUN}, + 'DET__Case=Gen|Number=Plur|PronType=Dem': {'morph': 'Case=Gen|Number=Plur|PronType=Dem', POS: DET}, + 'PRON__Gender=Fem,Masc|Number=Sing|Person=3|PronType=Prs,Tot': {'morph': 'Gender=Fem,Masc|Number=Sing|Person=3|PronType=Prs,Tot', POS: PRON}, + 'NOUN__Case=Gen|Definite=Ind|Gender=Fem|Number=Plur': {'morph': 'Case=Gen|Definite=Ind|Gender=Fem|Number=Plur', POS: NOUN}, + 'DET__Gender=Neut|Number=Sing|Polarity=Neg|PronType=Neg': {'morph': 'Gender=Neut|Number=Sing|Polarity=Neg|PronType=Neg', POS: DET}, + 'NOUN__Number=Plur': {'morph': 'Number=Plur', POS: NOUN}, + 'ADJ__Case=Gen|Definite=Ind|Degree=Pos|Number=Sing': {'morph': 'Case=Gen|Definite=Ind|Degree=Pos|Number=Sing', POS: ADJ}, + 'VERB__Definite=Ind|Number=Sing|VerbForm=Part': {'morph': 'Definite=Ind|Number=Sing|VerbForm=Part', POS: VERB}, + 'ADJ__Case=Gen|Definite=Def|Number=Sing|VerbForm=Part': {'morph': 'Case=Gen|Definite=Def|Number=Sing|VerbForm=Part', POS: ADJ}, + 'VERB__Mood=Ind|Tense=Past|VerbForm=Fin|Voice=Pass': {'morph': 'Mood=Ind|Tense=Past|VerbForm=Fin|Voice=Pass', POS: VERB}, + 'DET__Gender=Neut|Number=Sing|PronType=Dem,Ind': {'morph': 'Gender=Neut|Number=Sing|PronType=Dem,Ind', POS: DET}, + 'PRON__Animacy=Hum|Poss=Yes|PronType=Int': {'morph': 'Animacy=Hum|Poss=Yes|PronType=Int', POS: PRON}, + 'ADJ__Abbr=Yes': {'morph': 'Abbr=Yes', POS: ADJ}, + 'DET__Case=Gen|Gender=Masc|Number=Sing|PronType=Art': {'morph': 'Case=Gen|Gender=Masc|Number=Sing|PronType=Art', POS: DET}, + 'NOUN__Abbr=Yes|Definite=Def,Ind|Gender=Masc|Number=Sing': {'morph': 'Abbr=Yes|Definite=Def,Ind|Gender=Masc|Number=Sing', POS: NOUN}, + 'PRON__PronType=Prs': {'morph': 'PronType=Prs', POS: PRON}, + 'DET__Case=Gen|Gender=Fem|Number=Sing|PronType=Dem': {'morph': 'Case=Gen|Gender=Fem|Number=Sing|PronType=Dem', POS: DET}, + 'DET__Number=Plur|Poss=Yes|PronType=Rcp': {'morph': 'Number=Plur|Poss=Yes|PronType=Rcp', POS: DET}, + 'ADJ__Definite=Ind|Degree=Pos': {'morph': 'Definite=Ind|Degree=Pos', POS: ADJ}, + 'DET__Number=Plur|PronType=Art': {'morph': 'Number=Plur|PronType=Art', POS: DET}, + 'NUM__Case=Gen|Number=Plur|NumType=Card': {'morph': 'Case=Gen|Number=Plur|NumType=Card', POS: NUM}, + 'NOUN__Abbr=Yes|Definite=Def,Ind|Gender=Neut|Number=Plur,Sing': {'morph': 'Abbr=Yes|Definite=Def,Ind|Gender=Neut|Number=Plur,Sing', POS: NOUN}, + 'DET__Case=Gen|Number=Plur|PronType=Tot': {'morph': 'Case=Gen|Number=Plur|PronType=Tot', POS: DET}, + 'NOUN__Abbr=Yes|Definite=Def,Ind|Gender=Masc|Number=Plur,Sing': {'morph': 'Abbr=Yes|Definite=Def,Ind|Gender=Masc|Number=Plur,Sing', POS: NOUN}, + 'DET__Gender=Fem|Number=Sing|PronType=Int': {'morph': 'Gender=Fem|Number=Sing|PronType=Int', POS: DET}, + 'ADJ__Definite=Ind|Gender=Neut|Number=Sing': {'morph': 'Definite=Ind|Gender=Neut|Number=Sing', POS: ADJ}, + 'DET__Case=Gen|Definite=Ind|Gender=Masc|Number=Sing|PronType=Dem': {'morph': 'Case=Gen|Definite=Ind|Gender=Masc|Number=Sing|PronType=Dem', POS: DET}, + 'DET__Gender=Fem|Number=Sing|PronType=Prs': {'morph': 'Gender=Fem|Number=Sing|PronType=Prs', POS: DET}, + 'PRON__Animacy=Hum|Case=Gen,Nom|Number=Sing|PronType=Art,Prs': {'morph': 'Animacy=Hum|Case=Gen,Nom|Number=Sing|PronType=Art,Prs', POS: PRON}, + 'ADJ__Definite=Def|Degree=Pos|Gender=Masc|Number=Sing': {'morph': 'Definite=Def|Degree=Pos|Gender=Masc|Number=Sing', POS: ADJ}, + 'PRON__Animacy=Hum|Case=Gen|Number=Sing|PronType=Art,Prs': {'morph': 'Animacy=Hum|Case=Gen|Number=Sing|PronType=Art,Prs', POS: PRON}, + 'NUM__Gender=Fem|Number=Sing|NumType=Card': {'morph': 'Gender=Fem|Number=Sing|NumType=Card', POS: NUM}, + 'NOUN__Definite=Ind|Gender=Masc': {'morph': 'Definite=Ind|Gender=Masc', POS: NOUN}, + 'NOUN__Definite=Def|Number=Plur': {'morph': 'Definite=Def|Number=Plur', POS: NOUN}, + 'ADJ__Number=Sing|VerbForm=Part': {'morph': 'Number=Sing|VerbForm=Part', POS: ADJ}, + 'ADJ__Definite=Ind|Gender=Masc|Number=Sing|VerbForm=Part': {'morph': 'Definite=Ind|Gender=Masc|Number=Sing|VerbForm=Part', POS: ADJ}, + 'NOUN__Abbr=Yes|Gender=Masc': {'morph': 'Abbr=Yes|Gender=Masc', POS: NOUN}, + 'NOUN__Abbr=Yes|Case=Gen': {'morph': 'Abbr=Yes|Case=Gen', POS: NOUN}, + 'VERB__Abbr=Yes|Mood=Ind|Tense=Pres|VerbForm=Fin': {'morph': 'Abbr=Yes|Mood=Ind|Tense=Pres|VerbForm=Fin', POS: VERB}, + 'ADJ__Abbr=Yes|Degree=Pos': {'morph': 'Abbr=Yes|Degree=Pos', POS: ADJ}, + 'NOUN__Case=Gen|Gender=Fem': {'morph': 'Case=Gen|Gender=Fem', POS: NOUN}, + 'ADJ__Case=Gen|Degree=Cmp': {'morph': 'Case=Gen|Degree=Cmp', POS: ADJ}, + 'ADJ__Definite=Ind|Degree=Pos|Gender=Masc|Number=Sing': {'morph': 'Definite=Ind|Degree=Pos|Gender=Masc|Number=Sing', POS: ADJ}, + 'NOUN__Gender=Masc|Number=Sing': {'morph': 'Gender=Masc|Number=Sing', POS: NOUN}, +} + # + # "$(": {POS: PUNCT, "PunctType": "PUNCT"}, + # "$)": {POS: PUNCT, "PunctType": "PUNCT"}, + # # PUNCT + # # PUNCT + # "$,": {POS: PUNCT, "PunctType": "PUNCT"}, + # "$.": {POS: PUNCT, "PunctType": "PUNCT"}, + # "$\"": {POS: PUNCT, "PunctType": "PUNCT"}, + # "$-": {POS: PUNCT, "PunctType": "PUNCT"}, + # + # 'NOUN': {POS: NOUN}, + # 'PROPN': {POS: PROPN}, + # 'VERB': {POS: VERB}, + # 'PUNCT': {POS: PUNCT}, + # 'ADJ': {POS: ADJ}, + # 'ADP': {POS: ADP}, + # 'PART': {POS: PART}, + # 'DET': {POS: DET}, + # 'AUX': {POS: AUX}, + # 'PRON': {POS: PRON}, + # 'CCONJ': {POS: CCONJ}, + # 'NUM': {POS: NUM}, + # 'ADV': {POS: ADV}, + # 'SCONJ': {POS: SCONJ}, + # 'SYM': {POS: SYM}, + # 'X': {POS: X}, + # 'INTJ': {POS: INTJ}, # PUNCT # 'adj': {POS: ADJ}, @@ -51,5 +255,3 @@ TAG_MAP = { # 'symb': {POS: SYM}, # # 'ukjent': {POS: X}, # # 'verb': {POS: AUX}, #, VERB - -}