From b79c0681d3b42bec7b09d6dde39f32c057dd29b2 Mon Sep 17 00:00:00 2001 From: John Bauer Date: Thu, 26 Oct 2023 08:14:49 -0700 Subject: [PATCH 1/2] Update some NumForm to NumForm=Roman in the case of I, II, etc --- en_pud-ud-test.conllu | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-) diff --git a/en_pud-ud-test.conllu b/en_pud-ud-test.conllu index 1875bb5..c00657c 100644 --- a/en_pud-ud-test.conllu +++ b/en_pud-ud-test.conllu @@ -9187,7 +9187,7 @@ 11 Macedonian Macedonian ADJ JJ Degree=Pos 12 amod 12:amod _ 12 king king NOUN NN Number=Sing 15 nsubj 15:nsubj|20:nsubj _ 13 Amyntas Amyntas PROPN NNP Number=Sing 12 appos 12:appos _ -14 I i NUM CD NumForm=Word|NumType=Card 13 flat 13:flat _ +14 I i NUM CD NumForm=Roman|NumType=Card 13 flat 13:flat _ 15 accepted accept VERB VBD Mood=Ind|Tense=Past|VerbForm=Fin 0 root 0:root _ 16 the the DET DT Definite=Def|PronType=Art 18 det 18:det _ 17 Achaemenid achaemenid ADJ JJ Degree=Pos 18 amod 18:amod _ @@ -9557,7 +9557,7 @@ 3 king king NOUN NN Number=Sing 5 nsubj 5:nsubj _ 4 was be AUX VBD Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin 5 cop 5:cop _ 5 Mojmír Mojmír PROPN NNP Number=Sing 0 root 0:root _ -6 I i NUM CD NumForm=Word|NumType=Card 5 flat 5:flat _ +6 I i NUM CD NumForm=Roman|NumType=Card 5 flat 5:flat _ 7 ( ( PUNCT -LRB- _ 8 punct 8:punct SpaceAfter=No 8 ruled rule VERB VBD Mood=Ind|Tense=Past|VerbForm=Fin 5 parataxis 5:parataxis _ 9 830 830 NUM CD NumForm=Digit|NumType=Card 8 obj 8:obj SpaceAfter=No @@ -9576,7 +9576,7 @@ 6 and and CCONJ CC _ 7 cc 7:cc _ 7 replaced replace VERB VBD Mood=Ind|Tense=Past|VerbForm=Fin 4 conj 4:conj:and _ 8 Mojmír Mojmír PROPN NNP Number=Sing 7 obj 7:obj _ -9 I i NUM CD NumForm=Word|NumType=Card 8 flat 8:flat _ +9 I i NUM CD NumForm=Roman|NumType=Card 8 flat 8:flat _ 10 with with ADP IN _ 12 case 12:case _ 11 his he PRON PRP$ Gender=Masc|Number=Sing|Person=3|Poss=Yes|PronType=Prs 12 nmod:poss 12:nmod:poss _ 12 nephew nephew NOUN NN Number=Sing 7 obl 7:obl:with|15:nsubj|16:nsubj:xsubj _ @@ -12241,7 +12241,7 @@ 6 Kadesh Kadesh PROPN NNP Number=Sing 5 obj 5:obj SpaceAfter=No 7 , , PUNCT , _ 10 punct 10:punct _ 8 Ramesses Ramesses PROPN NNP Number=Sing 10 nsubj 10:nsubj _ -9 II ii NUM CD NumForm=Word|NumType=Card 8 flat 8:flat _ +9 II ii NUM CD NumForm=Roman|NumType=Card 8 flat 8:flat _ 10 committed commit VERB VBD Mood=Ind|Tense=Past|VerbForm=Fin 0 root 0:root _ 11 a a DET DT Definite=Ind|PronType=Art 14 det 14:det _ 12 major major ADJ JJ Degree=Pos 14 amod 14:amod _ @@ -12330,7 +12330,7 @@ 27 time time NOUN NN Number=Sing 24 obl 24:obl:since _ 28 of of ADP IN _ 29 case 29:case _ 29 Thutmose Thutmose PROPN NNP Number=Sing 27 nmod 27:nmod:of _ -30 III iii NUM CD NumForm=Word|NumType=Card 29 flat 29:flat _ +30 III iii NUM CD NumForm=Roman|NumType=Card 29 flat 29:flat _ 31 almost almost ADV RB _ 32 advmod 32:advmod _ 32 120 120 NUM CD NumForm=Digit|NumType=Card 33 nummod 33:nummod _ 33 years year NOUN NNS Number=Plur 34 obl:npmod 34:obl:npmod _ @@ -13033,7 +13033,7 @@ 19 Egyptian Egyptian ADJ JJ Degree=Pos 20 amod 20:amod _ 20 pharaoh pharaoh NOUN NN Number=Sing 16 nmod 16:nmod:by _ 21 Thutmose Thutmose PROPN NNP Number=Sing 20 appos 20:appos _ -22 III iii NUM CD NumForm=Word|NumType=Card 21 flat 21:flat SpaceAfter=No +22 III iii NUM CD NumForm=Roman|NumType=Card 21 flat 21:flat SpaceAfter=No 23 . . PUNCT . _ 5 punct 5:punct _ # sent_id = w01065021 @@ -15115,7 +15115,7 @@ 9 of of ADP IN _ 11 case 11:case _ 10 World world PROPN NN Number=Sing 11 compound 11:compound _ 11 War war PROPN NN Number=Sing 8 nmod 8:nmod:of _ -12 I i PROPN CD NumForm=Word|NumType=Card 11 compound 11:compound _ +12 I i PROPN CD NumForm=Roman|NumType=Card 11 compound 11:compound _ 13 to to ADP IN _ 15 case 15:case _ 14 increased increase VERB VBN Tense=Past|VerbForm=Part 15 amod 15:amod _ 15 mobility mobility NOUN NN Number=Sing 3 obl 3:obl:to _ @@ -17868,10 +17868,10 @@ 19 , , PUNCT , _ 20 punct 20:punct _ 20 including include VERB VBG VerbForm=Ger 18 acl 18:acl _ 21 Edward Edward PROPN NNP Number=Sing 20 obj 20:obj _ -22 IV iv NUM CD NumForm=Word|NumType=Card 21 flat 21:flat _ +22 IV iv NUM CD NumForm=Roman|NumType=Card 21 flat 21:flat _ 23 and and CCONJ CC _ 24 cc 24:cc _ 24 Richard Richard PROPN NNP Number=Sing 21 conj 20:obj|21:conj:and _ -25 III iii NUM CD NumForm=Word|NumType=Card 24 flat 24:flat SpaceAfter=No +25 III iii NUM CD NumForm=Roman|NumType=Card 24 flat 24:flat SpaceAfter=No 26 , , PUNCT , _ 28 punct 28:punct _ 27 Joan Joan PROPN NNP Number=Sing 28 nsubj 28:nsubj|30:nsubj:xsubj _ 28 became become VERB VBD Mood=Ind|Tense=Past|VerbForm=Fin 0 root 0:root _ @@ -23046,7 +23046,7 @@ 1 In in ADP IN _ 3 case 3:case _ 2 Pluviose Pluviose PROPN NNP Number=Sing 3 compound 3:compound _ 3 year year NOUN NN Number=Sing 23 obl 23:obl:in _ -4 III iii NUM CD NumForm=Word|NumType=Card 3 nummod 3:nummod _ +4 III iii NUM CD NumForm=Roman|NumType=Card 3 nummod 3:nummod _ 5 ( ( PUNCT -LRB- _ 8 punct 8:punct SpaceAfter=No 6 January January PROPN NNP Number=Sing 8 compound 8:compound SpaceAfter=No 7 - - PUNCT HYPH _ 8 punct 8:punct SpaceAfter=No @@ -23443,7 +23443,7 @@ 4 , , PUNCT , _ 8 punct 8:punct _ 5 Pope Pope PROPN NNP Number=Sing 8 nsubj 8:nsubj|17:nsubj _ 6 Paul Paul PROPN NNP Number=Sing 5 flat 5:flat _ -7 VI vi PROPN CD NumForm=Word|NumType=Card 5 flat 5:flat _ +7 VI vi PROPN CD NumForm=Roman|NumType=Card 5 flat 5:flat _ 8 removed remove VERB VBD Mood=Ind|Tense=Past|VerbForm=Fin 0 root 0:root _ 9 the the DET DT Definite=Def|PronType=Art 11 det 11:det _ 10 death death NOUN NN Number=Sing 11 compound 11:compound _ @@ -23614,7 +23614,7 @@ 10 existed exist VERB VBN Tense=Past|VerbForm=Part 0 root 0:root _ 11 under under ADP IN _ 12 case 12:case _ 12 Henry Henry PROPN NNP Number=Sing 10 obl 10:obl:under _ -13 I i PROPN CD NumForm=Word|NumType=Card 12 flat 12:flat _ +13 I i PROPN CD NumForm=Roman|NumType=Card 12 flat 12:flat _ 14 and and CCONJ CC _ 19 cc 19:cc _ 15 these these PRON DT Number=Plur|PronType=Dem 19 nsubj 19:nsubj _ 16 had have AUX VBD Mood=Ind|Tense=Past|VerbForm=Fin 19 aux 19:aux _ @@ -24412,13 +24412,13 @@ 12 daughters daughter NOUN NNS Number=Plur 24 nsubj 24:nsubj _ 13 of of ADP IN _ 14 case 14:case _ 14 Luis Luis PROPN NNP Number=Sing 12 nmod 12:nmod:of _ -15 X x PROPN CD NumForm=Word|NumType=Card 14 flat 14:flat SpaceAfter=No +15 X x PROPN CD NumForm=Roman|NumType=Card 14 flat 14:flat SpaceAfter=No 16 , , PUNCT , _ 17 punct 17:punct _ 17 Felipe Felipe PROPN NNP Number=Sing 14 conj 12:nmod:of|14:conj:and _ -18 V v PROPN CD NumForm=Word|NumType=Card 17 flat 17:flat _ +18 V v PROPN CD NumForm=Roman|NumType=Card 17 flat 17:flat _ 19 and and CCONJ CC _ 20 cc 20:cc _ 20 Carlos Carlos PROPN NNP Number=Sing 14 conj 12:nmod:of|14:conj:and _ -21 IV iv NUM CD NumForm=Word|NumType=Card 20 nummod 20:nummod Proper=True +21 IV iv NUM CD NumForm=Roman|NumType=Card 20 nummod 20:nummod Proper=True 22 would would AUX MD VerbForm=Fin 24 aux 24:aux _ 23 have have AUX VB VerbForm=Inf 24 aux 24:aux _ 24 had have VERB VBN Tense=Past|VerbForm=Part 0 root 0:root _ From 138bcd96c7b38ca6d1518e8d74acef1041271092 Mon Sep 17 00:00:00 2001 From: John Bauer Date: Thu, 26 Oct 2023 13:03:56 -0700 Subject: [PATCH 2/2] Update Roman numbers to be tagged NUM even when part of a proper noun --- en_pud-ud-test.conllu | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/en_pud-ud-test.conllu b/en_pud-ud-test.conllu index c00657c..c340523 100644 --- a/en_pud-ud-test.conllu +++ b/en_pud-ud-test.conllu @@ -15115,7 +15115,7 @@ 9 of of ADP IN _ 11 case 11:case _ 10 World world PROPN NN Number=Sing 11 compound 11:compound _ 11 War war PROPN NN Number=Sing 8 nmod 8:nmod:of _ -12 I i PROPN CD NumForm=Roman|NumType=Card 11 compound 11:compound _ +12 I i NUM CD NumForm=Roman|NumType=Card 11 compound 11:compound _ 13 to to ADP IN _ 15 case 15:case _ 14 increased increase VERB VBN Tense=Past|VerbForm=Part 15 amod 15:amod _ 15 mobility mobility NOUN NN Number=Sing 3 obl 3:obl:to _ @@ -23443,7 +23443,7 @@ 4 , , PUNCT , _ 8 punct 8:punct _ 5 Pope Pope PROPN NNP Number=Sing 8 nsubj 8:nsubj|17:nsubj _ 6 Paul Paul PROPN NNP Number=Sing 5 flat 5:flat _ -7 VI vi PROPN CD NumForm=Roman|NumType=Card 5 flat 5:flat _ +7 VI vi NUM CD NumForm=Roman|NumType=Card 5 flat 5:flat _ 8 removed remove VERB VBD Mood=Ind|Tense=Past|VerbForm=Fin 0 root 0:root _ 9 the the DET DT Definite=Def|PronType=Art 11 det 11:det _ 10 death death NOUN NN Number=Sing 11 compound 11:compound _ @@ -23614,7 +23614,7 @@ 10 existed exist VERB VBN Tense=Past|VerbForm=Part 0 root 0:root _ 11 under under ADP IN _ 12 case 12:case _ 12 Henry Henry PROPN NNP Number=Sing 10 obl 10:obl:under _ -13 I i PROPN CD NumForm=Roman|NumType=Card 12 flat 12:flat _ +13 I i NUM CD NumForm=Roman|NumType=Card 12 flat 12:flat _ 14 and and CCONJ CC _ 19 cc 19:cc _ 15 these these PRON DT Number=Plur|PronType=Dem 19 nsubj 19:nsubj _ 16 had have AUX VBD Mood=Ind|Tense=Past|VerbForm=Fin 19 aux 19:aux _ @@ -24412,10 +24412,10 @@ 12 daughters daughter NOUN NNS Number=Plur 24 nsubj 24:nsubj _ 13 of of ADP IN _ 14 case 14:case _ 14 Luis Luis PROPN NNP Number=Sing 12 nmod 12:nmod:of _ -15 X x PROPN CD NumForm=Roman|NumType=Card 14 flat 14:flat SpaceAfter=No +15 X x NUM CD NumForm=Roman|NumType=Card 14 flat 14:flat SpaceAfter=No 16 , , PUNCT , _ 17 punct 17:punct _ 17 Felipe Felipe PROPN NNP Number=Sing 14 conj 12:nmod:of|14:conj:and _ -18 V v PROPN CD NumForm=Roman|NumType=Card 17 flat 17:flat _ +18 V v NUM CD NumForm=Roman|NumType=Card 17 flat 17:flat _ 19 and and CCONJ CC _ 20 cc 20:cc _ 20 Carlos Carlos PROPN NNP Number=Sing 14 conj 12:nmod:of|14:conj:and _ 21 IV iv NUM CD NumForm=Roman|NumType=Card 20 nummod 20:nummod Proper=True