Skip to content

Commit

Permalink
#540 #557
Browse files Browse the repository at this point in the history
  • Loading branch information
@leoalenc
leoalenc committed Sep 12, 2024
1 parent 70f7947 commit 447f015
Showing 1 changed file with 27 additions and 24 deletions.
51 changes: 27 additions & 24 deletions data/corpus/universal-dependencies/yrl_complin-ud-test.conllu
View file
Original file line number Diff line number Diff line change
Expand Up @@ -25961,6 +25961,7 @@
# text_por_sec_source = Avila (2021)
# text_annotator = Juliana Lopes Gurgel
# acknowledgement = DACILAT Project, FAPESP's Process No. 2022/09158-5
# reviewer1 = Leonel Figueiredo de Alencar
1 Rewatá watá VERB V Mood=Imp,Ind|Number=Sing|Person=2|VerbForm=Fin 12 ccomp _ TokenRange=0:6
2 kurí kurí PART FUT Tense=Fut 1 advmod _ TokenRange=7:11
3 remuatiri muatiri VERB V Mood=Imp,Ind|Number=Sing|Person=2|VerbForm=Fin 1 parataxis _ TokenRange=12:21
Expand All @@ -25971,12 +25972,12 @@
8 ne ne PRON PRON2 Case=Gen|Number=Sing|Person=2|Poss=Yes|PronType=Prs 9 nmod:poss _ TokenRange=43:45
9 raíra-itá taíra NOUN N Number=Plur|Rel=Cont 6 obl _ TokenRange=46:55
10 irumu irumu ADP ADP AdpType=Post 9 case _ SpaceAfter=No|TokenRange=56:61
11 , , PUNCT PUNCT _ 12 punct _ TokenRange=61:62
11 , , PUNCT PUNCT _ 1 punct _ TokenRange=61:62
12 unheẽ nheẽ VERB V Mood=Ind|Person=3|VerbForm=Fin 0 root _ SpaceAfter=No|TokenRange=63:68
13 , , PUNCT PUNCT _ 14 punct _ TokenRange=68:69
14 paá paá PART RPRT Evident=Nfh|PartType=Mod 12 advmod _ SpaceAfter=No|TokenRange=70:73
15 , , PUNCT PUNCT _ 14 punct _ TokenRange=73:74
16 i i PRON PRON2 Case=Gen|Number=Sing|Person=3|PronType=Prs 12 obl _ TokenRange=75:76
16 i i PRON PRON2 Case=Gen|Number=Sing|Person=3|PronType=Prs 12 iobj _ TokenRange=75:76
17 xupé xupé ADP ADP AdpType=Post 16 case _ TokenRange=77:81
18 Kurasí kurasí NOUN N Number=Sing 12 nsubj _ SpaceAfter=No|TokenRange=82:88
19 . . PUNCT PUNCT _ 12 punct _ SpaceAfter=No|TokenRange=88:89
Expand All @@ -25997,21 +25998,22 @@
# title_por_orig = O urubu e o gavião
# title_eng = The vulture and the hawk
# acknowledgement = DACILAT Project, FAPESP's Process No. 2022/09158-5
# reviewer1 = Leonel Figueiredo de Alencar
1 Kuxiima kuxiima ADV ADVT AdvType=Tim 5 advmod _ SpaceAfter=No|TokenRange=0:7
2 , , PUNCT PUNCT _ 3 punct _ TokenRange=7:8
3 paá paá PART RPRT Evident=Nfh|PartType=Mod 5 advmod _ SpaceAfter=No|TokenRange=9:12
4 , , PUNCT PUNCT _ 3 punct _ TokenRange=12:13
5 aikwé aikwé PART EXST PartType=Exs 0 root _ TokenRange=14:19
6 siiya siiya DET INDQ PronType=Ind 7 det _ TokenRange=20:25
7 mira-itá mira NOUN N Number=Plur 5 nsubj _ SpaceAfter=No|TokenRange=26:34
8 , , PUNCT PUNCT _ 11 punct _ TokenRange=34:35
8 , , PUNCT PUNCT _ 12 punct _ TokenRange=34:35
9 amú-itá amú DET IND Number=Plur|PronType=Ind 11 det _ TokenRange=36:43
10 ta ta PRON PRON2 Case=Gen|Number=Plur|Person=3|Poss=Yes|PronType=Prs 11 expl _ TokenRange=44:46
11 mirasawa mirasawa NOUN N Number=Sing 7 appos _ TokenRange=47:58
12 Tupí tupí NOUN N Number=Sing 11 nmod:poss _ SpaceAfter=No|TokenRange=56:60
10 ta ta PRON PRON2 Case=Gen|Number=Plur|Person=3|Poss=Yes|PronType=Prs 11 nmod:poss _ TokenRange=44:46
11 mirasawa mirasawa NOUN N Number=Sing 12 nsubj _ TokenRange=47:58
12 Tupí tupí NOUN N Number=Sing 5 parataxis _ SpaceAfter=No|TokenRange=56:60
13 , , PUNCT PUNCT _ 15 punct _ TokenRange=60:61
14 amú-itá amú DET IND Number=Plur|PronType=Ind 15 det _ TokenRange=62:69
15 Baré baré NOUN N Number=Sing 7 appos _ SpaceAfter=No|TokenRange=70:74
14 amú-itá amú PRON IND Number=Plur|PronType=Ind 15 nsubj _ TokenRange=62:69
15 Baré baré NOUN N Number=Sing 5 parataxis _ SpaceAfter=No|TokenRange=70:74
16 . . PUNCT PUNCT _ 5 punct _ SpaceAfter=No|TokenRange=74:75

# sent_id = Casasnovas2006:12:2:168
Expand All @@ -26026,6 +26028,7 @@
# text_por_sec_source = Avila (2021)
# text_annotator = Juliana Lopes Gurgel
# acknowledgement = DACILAT Project, FAPESP's Process No. 2022/09158-5
# reviewer1 = Leonel Figueiredo de Alencar
1 Nhaã-itá nhaã PRON DEMS Deixis=Remt|Number=Plur|PronType=Dem 7 nsubj _ SpaceAfter=No|TokenRange=0:8
2 , , PUNCT PUNCT _ 3 punct _ TokenRange=8:9
3 paá paá PART RPRT Evident=Nfh|PartType=Mod 7 advmod _ SpaceAfter=No|TokenRange=10:13
Expand All @@ -26037,14 +26040,14 @@
9 . . PUNCT PUNCT _ 7 punct _ SpaceAfter=No|TokenRange=35:36

# sent_id = Casasnovas2006:12:3:169
# text = Nhaã Tupí mira-itá pitérupi, paá, aikwé yepé kunhã-itá i sera waá Adana.
# text = Nhaã Tupí mira-itá pitérupi, paá, aikwé yepé kunhatãi sera waá Adana.
# text_eng = TODO
# text_por = Na tribo Tupi, havia uma índia cujo nome era ADANA.
# text_por_orig = Na tribo Tupi, havia uma índia cujo nome era ADANA,
# text_source = p. 98, No. 3
# text_orig = Nhaã Tupí miraitá pitérupi, paá, aikwé yepé kunhaitãi sera waá Adana.
# text_annotator = Juliana Lopes Gurgel
# acknowledgement = DACILAT Project, FAPESP's Process No. 2022/09158-5
# reviewer1 = Leonel Figueiredo de Alencar
1 Nhaã nhaã DET DEMS Deixis=Remt|Number=Sing|PronType=Dem 3 det _ TokenRange=0:4
2 Tupí tupí NOUN N Number=Sing 3 nmod:poss _ TokenRange=5:9
3 mira-itá mira NOUN N Number=Plur 4 nmod:poss _ TokenRange=10:18
Expand All @@ -26055,13 +26058,12 @@
7 paá paá PART RPRT Evident=Nfh|PartType=Mod 9 advmod _ SpaceAfter=No|TokenRange=29:32
8 , , PUNCT PUNCT _ 7 punct _ TokenRange=32:33
9 aikwé aikwé PART EXST PartType=Exs 0 root _ TokenRange=34:39
10 yepé yepé DET ART Definite=Ind|PronType=Art 9 nsubj _ TokenRange=40:44
11 kunhã-itá kunhã NOUN N Number=Plur 10 nmod _ TokenRange=45:54
12 i i PRON PRON2 Case=Gen|Number=Sing|Person=3|Poss=Yes|PronType=Prs 13 nmod:poss _ TokenRange=55:56
13 sera sera NOUN N Number=Sing|Number[psor]=Sing|Person[psor]=3|Rel=NCont 15 nsubj _ TokenRange=59:63
14 waá waá PRON REL Number=Sing|PronType=Rel 13 nmod:poss _ TokenRange=62:65
15 Adana adana PROPN PROPN _ 10 acl:relcl _ SpaceAfter=No|TokenRange=66:71
16 . . PUNCT PUNCT _ 9 punct _ SpaceAfter=No|TokenRange=71:72
10 yepé yepé DET ART Definite=Ind|PronType=Art 11 det _ TokenRange=40:44
11 kunhatãi kunhatãi NOUN N Number=Sing 9 nsubj _ TokenRange=45:53
12 sera sera NOUN N Number=Sing|Number[psor]=Sing|Person[psor]=3|Rel=NCont 14 nsubj _ TokenRange=56:60
13 waá waá PRON REL Number=Sing|PronType=Rel 12 nmod:poss _ TokenRange=59:62
14 Adana adana PROPN PROPN _ 11 acl:relcl _ SpaceAfter=No|TokenRange=63:68
15 . . PUNCT PUNCT _ 9 punct _ SpaceAfter=No|TokenRange=68:69

# sent_id = Casasnovas2006:12:4:170
# text = I paya, paá, yepé tuxawa ukwawa piri waá panhẽ mira suí.
Expand Down Expand Up @@ -26091,26 +26093,27 @@
# sent_id = Casasnovas2006:12:6:172
# text = Adana, paá, uyumunhã, usú uikú, upitá yepé kunhamukú puranga, puranga piri panhẽ kunhamukú suí.
# text_eng = TODO
# text_por = Adana cresceu e tomou-se uma linda índia, a mais bonita de todas as moças.
# text_por = Adana cresceu e tornou-se uma linda índia, a mais bonita de todas as moças.
# text_source = p. 98, No. 7-8
# text_orig = Adana, paá, uyumunhã, usú uikú, upitá yepé kunhã-mukú puranga, puranga piri panhé kunhã-mukú suí.
# text_annotator = Juliana Lopes Gurgel
# acknowledgement = DACILAT Project, FAPESP's Process No. 2022/09158-5
# reviewer1 = Leonel Figueiredo de Alencar
1 Adana adana PROPN PROPN _ 5 nsubj _ SpaceAfter=No|TokenRange=0:5
2 , , PUNCT PUNCT _ 3 punct _ TokenRange=5:6
3 paá paá PART RPRT Evident=Nfh|PartType=Mod 5 advmod _ SpaceAfter=No|TokenRange=7:10
4 , , PUNCT PUNCT _ 3 punct _ TokenRange=10:11
5 uyumunhã yumunhã VERB V Mood=Ind|Person=3|VerbForm=Fin 0 root _ SpaceAfter=No|TokenRange=12:20
6 , , PUNCT PUNCT _ 7 punct _ TokenRange=20:21
7 usú sú AUX AUXFR Mood=Ind|Person=3|VerbForm=Fin 5 aux _ TokenRange=22:25
8 uikú ikú AUX AUXFS Mood=Ind|Person=3|VerbForm=Fin 5 aux _ SpaceAfter=No|TokenRange=26:30
9 , , PUNCT PUNCT _ 10 punct _ TokenRange=30:31
6 , , PUNCT PUNCT _ 10 punct _ TokenRange=20:21
7 usú sú AUX AUXFR Mood=Ind|Person=3|VerbForm=Fin 10 aux _ TokenRange=22:25
8 uikú ikú AUX AUXFS Mood=Ind|Person=3|VerbForm=Fin 10 aux _ SpaceAfter=No|TokenRange=26:30
9 , , PUNCT PUNCT _ 8 punct _ TokenRange=30:31
10 upitá pitá VERB V Mood=Ind|Person=3|VerbForm=Fin 5 parataxis _ TokenRange=32:37
11 yepé yepé DET ART Definite=Ind|PronType=Art 12 det _ TokenRange=38:42
12 kunhamukú kunhamukú NOUN N Number=Sing 10 obj _ TokenRange=43:52
12 kunhamukú kunhamukú NOUN N Number=Sing 10 xcomp _ TokenRange=43:52
13 puranga puranga ADJ A _ 12 amod _ SpaceAfter=No|TokenRange=53:60
14 , , PUNCT PUNCT _ 15 punct _ TokenRange=60:61
15 puranga puranga ADJ A _ 12 acl:relcl _ TokenRange=62:69
15 puranga puranga ADJ A _ 13 conj _ TokenRange=62:69
16 piri piri ADV ADVG AdvType=Deg 15 advmod _ TokenRange=70:74
17 panhẽ panhẽ DET TOT PronType=Tot 18 det _ TokenRange=75:80
18 kunhamukú kunhamukú NOUN N Number=Sing 15 obl _ TokenRange=81:90
Expand Down

0 comments on commit 447f015

Please sign in to comment.