diff --git a/data/corpus/universal-dependencies/yrl_complin-ud-test.conllu b/data/corpus/universal-dependencies/yrl_complin-ud-test.conllu index 22fe6e3..2b65439 100644 --- a/data/corpus/universal-dependencies/yrl_complin-ud-test.conllu +++ b/data/corpus/universal-dependencies/yrl_complin-ud-test.conllu @@ -12518,7 +12518,7 @@ 3 paá paá PART RPRT Evident=Nfh|PartType=Mod 1 advmod _ TokenRange=11:14 4 yumimisawa yumimisawa NOUN N Number=Sing 1 obl _ TokenRange=15:25 5 rupí rupí ADP ADP AdpType=Post 4 case _ SpaceAfter=No|TokenRange=26:30 -6 , , PUNCT PUNCT _ 8 punct _ TokenRange=30:31 +6 , , PUNCT PUNCT _ 1 punct _ TokenRange=30:31 7 usú sú AUX AUXFR Mood=Ind|Person=3|VerbForm=Fin 8 aux _ TokenRange=32:35 8 usikari sikari VERB V Mood=Ind|Person=3|VerbForm=Fin 0 root _ TokenRange=36:43 9 Adana adana PROPN PROPN _ 8 obj _ SpaceAfter=No|TokenRange=44:49 @@ -26697,7 +26697,6 @@ # text_source = p. 99, No. 14 # text_orig = Asuí, paá, Buburi mayé Adana, aintá usaã ta piá upé ta uyuputari. # text_annotator = Juliana Lopes Gurgel -# comment = Ver issue relacionada: CompLin/nheengatu/issues/582. # acknowledgement = DACILAT Project, FAPESP's Process No. 2022/09158-5 # inputline = Asuí/advt, paá, Buburi/=p mayé/advla Adana/=p, aintá/pron usaã ta/pron2 piá upé/adp ta/pron uyuputari/=mid. # reviewer1 = Leonel Figueiredo de Alencar @@ -26806,8 +26805,9 @@ # text_sec_source = Avila (2021) # text_por_sec_source = Avila (2021) # acknowledgement = DACILAT Project, FAPESP's Process No. 2022/09158-5 -# comment = sentence already in 'yrl_complin-ud-test.conllu' (Avila2021:0:0:555) +# cross_reference = Avila2021:0:0:555 # inputline = Buburi/=p unheẽ i/pron2 xupé uyuka arã/sconj aé/pron umendari rundé/sconj. +# reviewer1 = Leonel Figueiredo de Alencar 1 Buburi buburi PROPN PROPN _ 2 nsubj _ TokenRange=0:6 2 unheẽ nheẽ VERB V Mood=Ind|Person=3|VerbForm=Fin 0 root _ TokenRange=7:12 3 i i PRON PRON2 Case=Gen|Number=Sing|Person=3|PronType=Prs 2 iobj _ TokenRange=13:14 @@ -26878,19 +26878,16 @@ 17 . . PUNCT PUNCT _ 12 punct _ SpaceAfter=No|TokenRange=74:75 # sent_id = Casasnovas2006:12:19:185 -# text = Usika ramé, paá, yumimisawa rupí, usú usikari Adana, uwasemu aé yepé uka upé anhuíra. +# text = Usika ramé, paá, yumimisawa rupí, usú usikari Adana, wasemu aé yepé uka upé anhuíra. # text_eng = TODO # text_por = Tendo chegado à festa despercebido procurou Adana e a encontrou numa casa sozinha. # text_source = p. 99, No. 21 # text_orig = Usika ramé, paá, yumimisawa rupí, usú usikái Adana, wasemu aé yepé uka upé anhuíra. # text_annotator = Juliana Lopes Gurgel -# text_sec = Usika ramé paá, yumimisawa rupí usú usikari Adana, uwasemu aé yepé uka upé anhuíra. (...) -# text_por_sec = Quando chegou, foi encobertamente procurar Adana, encontrou-a numa casa sozinha. (...) -# text_sec_source = Avila (2021) -# text_por_sec_source = Avila (2021) # acknowledgement = DACILAT Project, FAPESP's Process No. 2022/09158-5 -# comment = sentence already in 'yrl_complin-ud-test.conllu' (Avila2021:33:1:420) -# inputline = Usika ramé/sconj, paá, yumimisawa rupí, usú usikari Adana/=p, uwasemu aé/pron yepé/art uka upé/adp anhuíra. +# cross_reference = Avila2021:33:1:420 +# inputline = Usika ramé/sconj, paá, yumimisawa rupí, usú usikari Adana/=p, wasemu/=typo:c|uwasemu aé/pron yepé/art uka upé/adp anhuíra. +# reviewer1 = Leonel Figueiredo de Alencar 1 Usika sika VERB V Mood=Ind|Person=3|VerbForm=Fin 10 advcl _ TokenRange=0:5 2 ramé ramé SCONJ SCONJ _ 1 mark _ SpaceAfter=No|TokenRange=6:10 3 , , PUNCT PUNCT _ 4 punct _ TokenRange=10:11 @@ -26898,12 +26895,12 @@ 5 , , PUNCT PUNCT _ 4 punct _ TokenRange=15:16 6 yumimisawa yumimisawa NOUN N Number=Sing 1 obl _ TokenRange=17:27 7 rupí rupí ADP ADP AdpType=Post 6 case _ SpaceAfter=No|TokenRange=28:32 -8 , , PUNCT PUNCT _ 10 punct _ TokenRange=32:33 +8 , , PUNCT PUNCT _ 1 punct _ TokenRange=32:33 9 usú sú AUX AUXFR Mood=Ind|Person=3|VerbForm=Fin 10 aux _ TokenRange=34:37 10 usikari sikari VERB V Mood=Ind|Person=3|VerbForm=Fin 0 root _ TokenRange=38:45 11 Adana adana PROPN PROPN _ 10 obj _ SpaceAfter=No|TokenRange=46:51 12 , , PUNCT PUNCT _ 13 punct _ TokenRange=51:52 -13 uwasemu wasemu VERB V Mood=Ind|Person=3|VerbForm=Fin 10 parataxis _ TokenRange=53:60 +13 wasemu wasemu VERB V Mood=Ind|Person=3|Typo=Yes|VerbForm=Fin 10 parataxis _ CorrectForm=uwasemu|TokenRange=53:59 14 aé aé PRON PRON Number=Sing|Person=3|PronType=Prs 13 obj _ TokenRange=61:63 15 yepé yepé DET ART Definite=Ind|PronType=Art 16 det _ TokenRange=64:68 16 uka uka NOUN N Number=Sing|Rel=Abs 13 obl _ TokenRange=69:72 @@ -26998,8 +26995,9 @@ # text_sec_source = Avila (2021) # text_por_sec_source = Avila (2021) # acknowledgement = DACILAT Project, FAPESP's Process No. 2022/09158-5 -# comment = sentence already in 'yrl_complin-ud-test.conllu' (Avila2021:0:0:511) +# cross_reference = Avila2021:0:0:511 # inputline = I/pron2 piaiwasawa, paá, upisika igara usú arã/sconj aintá/pron2 rakwera/n. +# reviewer1 = Leonel Figueiredo de Alencar 1 I i PRON PRON2 Case=Gen|Number=Sing|Person=3|Poss=Yes|PronType=Prs 2 nmod:poss _ TokenRange=0:1 2 piaiwasawa piaiwasawa NOUN N Number=Sing 6 obl _ SpaceAfter=No|TokenRange=2:12 3 , , PUNCT PUNCT _ 4 punct _ TokenRange=12:13 @@ -27073,8 +27071,9 @@ # text_sec_source = Avila (2021) # text_por_sec_source = Avila (2021) # acknowledgement = DACILAT Project, FAPESP's Process No. 2022/09158-5 -# comment = sentence already in 'yrl_complin-ud-test.conllu' (Avila2021:30:1:346) +# cross_reference = Avila2021:30:1:346 # inputline = Aintá/pron umaramunha pukusawa/sconj, paá, ií upurakari aintá/pron2 igara upé/adp. +# reviewer1 = Leonel Figueiredo de Alencar 1 Aintá aintá PRON PRON Number=Plur|Person=3|PronType=Prs 2 nsubj _ TokenRange=0:5 2 umaramunha maramunha VERB V Mood=Ind|Person=3|VerbForm=Fin 8 advcl _ TokenRange=6:16 3 pukusawa pukusawa SCONJ SCONJ _ 2 mark _ SpaceAfter=No|TokenRange=17:25 @@ -27094,15 +27093,16 @@ # text_por = Até que todos se alagaram no meio do rio. # text_por_orig = Até que todos se alagaram no meio do rio # text_source = p. 99, No. 29 -# text_orig = Ape, paá,aintá uyupipika paraná pitérupi, +# text_orig = Ape, paá, aintá uyupipika paraná pitérupi, # text_annotator = Juliana Lopes Gurgel # text_sec = Ape paá aintá uyupipika paraná pitérupi. # text_por_sec = Aí eles afundaram no meio do rio. # text_sec_source = Avila (2021) # text_por_sec_source = Avila (2021) # acknowledgement = DACILAT Project, FAPESP's Process No. 2022/09158-5 -# comment = sentence already in 'yrl_complin-ud-test.conllu' (Avila2021:30:2:347) +# cross_reference = Avila2021:30:2:347 # inputline = Ape/advt, paá, aintá/pron uyupipika paraná pitérupi. +# reviewer1 = Leonel Figueiredo de Alencar 1 Ape ape ADV ADVT AdvType=Tim 6 advmod _ SpaceAfter=No|TokenRange=0:3 2 , , PUNCT PUNCT _ 3 punct _ TokenRange=3:4 3 paá paá PART RPRT Evident=Nfh|PartType=Mod 6 advmod _ SpaceAfter=No|TokenRange=5:8 @@ -27143,14 +27143,16 @@ # text_sec_source = Avila (2021) # text_por_sec_source = Avila (2021) # acknowledgement = DACILAT Project, FAPESP's Process No. 2022/09158-5 -# comment = sentence already in 'yrl_complin-ud-test.conllu' (Avila2021:18:2:176) +# cross_reference = Avila2021:18:2:176 # inputline = Uyeréu amú/ind pirantá/n turusú/a piri/advg, sera Buburi/=p. +# reviewer1 = Leonel Figueiredo de Alencar +# review_status = ongoing 1 Uyeréu yeréu VERB V Mood=Ind|Person=3|VerbForm=Fin 0 root _ TokenRange=0:6 2 amú amú DET IND Number=Sing|PronType=Ind 3 det _ TokenRange=7:10 3 pirantá pirantá NOUN N Number=Sing 1 xcomp _ TokenRange=11:18 -4 turusú turusú ADJ A _ 3 acl:relcl _ TokenRange=19:25 +4 turusú turusú ADJ A _ 3 amod _ TokenRange=19:25 5 piri piri ADV ADVG AdvType=Deg 4 advmod _ SpaceAfter=No|TokenRange=26:30 -6 , , PUNCT PUNCT _ 4 punct _ TokenRange=30:31 +6 , , PUNCT PUNCT _ 8 punct _ TokenRange=30:31 7 sera sera NOUN N Number=Sing|Number[psor]=Sing|Person[psor]=3|Rel=NCont 8 nsubj _ TokenRange=32:36 8 Buburi buburi PROPN PROPN _ 3 parataxis _ SpaceAfter=No|TokenRange=37:43 9 . . PUNCT PUNCT _ 1 punct _ SpaceAfter=No|TokenRange=43:44 @@ -27167,7 +27169,7 @@ # text_sec_source = Avila (2021) # text_por_sec_source = Avila (2021) # acknowledgement = DACILAT Project, FAPESP's Process No. 2022/09158-5 -# comment = a próxima sentença desta lenda já está no 'yrl_complin-ud-test.conllu' (Avila2021:0:0:517) +# next = Avila2021:0:0:517 # inputline = Yawé/adva resewara/sconj nhaã musapiri, paá, iké pawa/total tẽ/foc ta/pron uikú, yané/pron2 tawa upé/adp. 1 Yawé yawé ADV ADVA AdvType=Man 8 advmod _ TokenRange=0:4 2 resewara resewara SCONJ SCONJ Rel=Cont 1 fixed _ TokenRange=5:13