Skip to content

Commit

Permalink
#540
Browse files Browse the repository at this point in the history
  • Loading branch information
@leoalenc
leoalenc committed Sep 10, 2024
1 parent c33b210 commit 5576615
Showing 1 changed file with 118 additions and 0 deletions.
118 changes: 118 additions & 0 deletions data/corpus/universal-dependencies/yrl_complin-ud-test.conllu
View file
Original file line number Diff line number Diff line change
Expand Up @@ -25836,6 +25836,124 @@
10 rupí rupí ADP ADP AdpType=Post 9 case _ SpaceAfter=No|TokenRange=41:45
11 . . PUNCT PUNCT _ 8 punct _ SpaceAfter=No|TokenRange=45:46

# sent_id = Casasnovas2006:11:30:161
# text = Aintá usika, paá, pitérupi aintá umaã, paá, isima mirĩ, mamé, paá, muíri ara Wakurawá usuwera ukiri.
# text_eng = TODO
# text_por = Chegando lá no meio viram um lugar limpo onde todos os dias o Bacurau ia dormir.
# text_source = p. 95, No. 39-40
# text_orig = Aintá usika, paá, pitérupi aintá umaã, paá, isima mirí, mamé, paá, muíri ara Wakurawá usuwera ukiri.
# text_orig = Kuíri yasu yamaã neyara, unheé, paá, Wakurawá supé.
# text_sec = [...] aintá umaã paá isima mirĩ mamé paá muíri ara wakurawá usuwera ukiri.
# text_por_sec = [...] eles viram um pequeno lugar limpo onde todos os dias o bacurau ia dormir.
# text_sec_source = Avila (2021)
# 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 Aintá aintá PRON PRON Number=Plur|Person=3|PronType=Prs 2 nsubj _ TokenRange=0:5
2 usika sika VERB V Mood=Ind|Person=3|VerbForm=Fin 0 root _ SpaceAfter=No|TokenRange=6:11
3 , , PUNCT PUNCT _ 4 punct _ TokenRange=11:12
4 paá paá PART RPRT Evident=Nfh|PartType=Mod 2 advmod _ SpaceAfter=No|TokenRange=13:16
5 , , PUNCT PUNCT _ 4 punct _ TokenRange=16:17
6-7 pitérupi _ _ _ _ _ _ _ TokenRange=18:26
6 pitera pitera NOUN N Number=Sing 2 obl _ _
7 upé upé ADP ADP AdpType=Post|Clitic=Yes 6 case _ _
8 aintá aintá PRON PRON Number=Plur|Person=3|PronType=Prs 9 nsubj _ TokenRange=27:32
9 umaã maã VERB V Mood=Ind|Person=3|VerbForm=Fin 2 parataxis _ SpaceAfter=No|TokenRange=33:37
10 , , PUNCT PUNCT _ 11 punct _ TokenRange=37:38
11 paá paá PART RPRT Evident=Nfh|PartType=Mod 9 advmod _ SpaceAfter=No|TokenRange=39:42
12 , , PUNCT PUNCT _ 11 punct _ TokenRange=42:43
13 isima isima NOUN N Number=Sing 9 obj _ TokenRange=44:49
14 mirĩ mirĩ ADJ A _ 13 amod _ SpaceAfter=No|TokenRange=50:54
15 , , PUNCT PUNCT _ 16 punct _ TokenRange=54:55
16 mamé mamé ADV ADVLC AdvType=Loc|PronType=Rel 25 advmod _ SpaceAfter=No|TokenRange=56:60
17 , , PUNCT PUNCT _ 18 punct _ TokenRange=60:61
18 paá paá PART RPRT Evident=Nfh|PartType=Mod 25 advmod _ SpaceAfter=No|TokenRange=62:65
19 , , PUNCT PUNCT _ 18 punct _ TokenRange=65:66
20 muíri muíri DET TOT PronType=Tot 21 det _ TokenRange=67:72
21 ara ara NOUN N Number=Sing 25 obl _ TokenRange=73:76
22 Wakurawá wakurawá NOUN N Number=Sing 25 nsubj _ TokenRange=77:85
23-24 usuwera _ _ _ _ _ _ _ TokenRange=86:93
23 usú sú AUX AUXFR Mood=Ind|Person=3|VerbForm=Fin 25 aux _ _
24 wera wera PART FREQ Aspect=Freq|Clitic=Yes|Tense=Past 25 advmod _ _
25 ukiri kiri VERB V Mood=Ind|Person=3|VerbForm=Fin 13 acl:relcl _ SpaceAfter=No|TokenRange=94:99
26 . . PUNCT PUNCT _ 2 punct _ SpaceAfter=No|TokenRange=99:100

# sent_id = Casasnovas2006:11:31:162
# text = Aape, paá, Kurasí tuyué i piaíwa upurandú Wakurawá suí: Anhuntẽ ne murakí kwá.
# text_eng = TODO
# text_por = Aí o velho Sol ficou bravo e perguntou a Bacurau: Somente isto é o seu trabalho?
# text_source = p. 96, No. 41-42
# text_orig = Aápe, paá, Kurasí tuyué ipiaíwa upurandú Wakurawá suí: Anhute ne muraki kwa.
# text_sec = Anhuntẽ ne murakí kwá?
# text_por_sec = É só isso o seu trabalho?
# text_sec_source = Avila (2021)
# 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 Aape aape ADV ADVT AdvType=Tim 8 advmod _ SpaceAfter=No|TokenRange=0:4
2 , , PUNCT PUNCT _ 3 punct _ TokenRange=4:5
3 paá paá PART RPRT Evident=Nfh|PartType=Mod 8 advmod _ SpaceAfter=No|TokenRange=6:9
4 , , PUNCT PUNCT _ 3 punct _ TokenRange=9:10
5 Kurasí kurasí NOUN N Number=Sing 6 nmod:poss _ TokenRange=11:17
6 tuyué tuyué NOUN N Number=Sing 8 nsubj _ TokenRange=18:23
7 i i PRON PRON2 Case=Gen|Number=Sing|Person=3|PronType=Prs 8 expl _ TokenRange=24:25
8 piaíwa piaíwa VERB V2 _ 0 root _ TokenRange=26:32
9 upurandú purandú VERB V Mood=Ind|Person=3|VerbForm=Fin 8 parataxis _ TokenRange=33:41
10 Wakurawá wakurawá NOUN N Number=Sing 9 obl _ TokenRange=42:50
11 suí suí ADP ADP AdpType=Post 10 case _ SpaceAfter=No|TokenRange=51:54
12 : : PUNCT PUNCT _ 15 punct _ TokenRange=54:55
13 Anhuntẽ anhuntẽ ADV ADV _ 15 advmod _ TokenRange=56:63
14 ne ne PRON PRON2 Case=Gen|Number=Sing|Person=2|Poss=Yes|PronType=Prs 15 nmod:poss _ TokenRange=64:66
15 murakí murakí NOUN N Number=Sing 9 ccomp _ TokenRange=67:73
16 kwá kwá PRON DEMX Deixis=Prox|Number=Sing|PronType=Dem 15 nsubj _ SpaceAfter=No|TokenRange=74:77
17 . . PUNCT PUNCT _ 8 punct _ SpaceAfter=No|TokenRange=77:78

# sent_id = Casasnovas2006:11:32:163
# text = Umbaá rẽ ambá, anheẽ rakú indé arã, unheẽ, paá, Wakurawá.
# text_eng = TODO
# text_por = Ainda não terminei, eu lhe falei, disse o Bacurau.
# text_source = p. 96, No. 43
# text_orig = Umbaré ambá, anheé rakú indé arã, unheé, paá, Wakurawá
# text_sec = ― Anhunté ne murakí kwá? ― Umbaá rẽ ambá, anheẽ rakú indé arã, [...].
# text_por_sec = ― É só isso o seu trabalho? ― Eu ainda não terminei, eu te disse, [...].
# text_sec_source = Avila (2021)
# 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 Umbaá umbaá PART NEG PartType=Neg|Polarity=Neg 3 advmod _ TokenRange=0:5
2 rẽ rẽ PART IMPF _ 3 advmod _ TokenRange=6:8
3 ambá mbá VERB V Mood=Ind|Number=Sing|Person=1|VerbForm=Fin 5 ccomp _ SpaceAfter=No|TokenRange=9:13
4 , , PUNCT PUNCT _ 3 punct _ TokenRange=13:14
5 anheẽ nheẽ VERB V Mood=Ind|Number=Sing|Person=1|VerbForm=Fin 10 ccomp _ TokenRange=15:20
6 rakú rakú PART CERT PartType=Mod 5 advmod _ TokenRange=21:25
7 indé indé PRON PRON Number=Sing|Person=2|PronType=Prs 5 iobj _ TokenRange=26:30
8 arã arã ADP ADP AdpType=Post 7 case _ SpaceAfter=No|TokenRange=31:34
9 , , PUNCT PUNCT _ 5 punct _ TokenRange=34:35
10 unheẽ nheẽ VERB V Mood=Ind|Person=3|VerbForm=Fin 0 root _ SpaceAfter=No|TokenRange=36:41
11 , , PUNCT PUNCT _ 12 punct _ TokenRange=41:42
12 paá paá PART RPRT Evident=Nfh|PartType=Mod 10 advmod _ SpaceAfter=No|TokenRange=43:46
13 , , PUNCT PUNCT _ 12 punct _ TokenRange=46:47
14 Wakurawá wakurawá NOUN N Number=Sing 10 nsubj _ SpaceAfter=No|TokenRange=48:56
15 . . PUNCT PUNCT _ 10 punct _ SpaceAfter=No|TokenRange=56:57

# sent_id = Casasnovas2006:11:33:164
# text = Indé yepé atimamanha.
# text_eng = TODO
# text_por = Você é preguiçoso,
# text_source = p. 96, No. 44
# text_orig = Indé yepé atima manha.
# text_annotator = Juliana Lopes Gurgel
# acknowledgement = DACILAT Project, FAPESP's Process No. 2022/09158-5
# reviewer1 = Leonel Figueiredo de Alencar
# inputline = Indé yepé/art atimamanha/n@.
1 Indé indé PRON PRON Number=Sing|Person=2|PronType=Prs 3 nsubj _ TokenRange=0:4
2 yepé yepé DET ART Definite=Ind|PronType=Art 3 det _ TokenRange=5:9
3 atimamanha atimamanha NOUN N Number=Sing 0 root _ SpaceAfter=No|TokenRange=10:20
4 . . PUNCT PUNCT _ 3 punct _ SpaceAfter=No|TokenRange=20:21

# sent_id = Casasnovas2006:7:1:1
# text = Yepé ara paá taína-itá taunheẽ ta ramunha tamakwarí tuyué supé: — Abú, puxiwera paá marandua yandé.
# text_eng = One day, they say, children said to their grandfather, old Tamaquari: "Grandpa, we have bad news.
Expand Down

0 comments on commit 5576615

Please sign in to comment.