From 2abf015889ce5b595438d3c592a43010e3ff42f6 Mon Sep 17 00:00:00 2001 From: Nathan Schneider Date: Sat, 16 Nov 2024 23:13:35 -0500 Subject: [PATCH] fix subjects in non-subject contexts (UniversalDependencies/docs#1066) --- en_ewt-ud-train.conllu | 32 +++++++++---------- .../20111108094927AA5NjHj_ans.xml.conllu | 18 +++++------ ...7697318f71f_ENG_20031006_163200.xml.conllu | 2 +- .../sources/reviews/135010.xml.conllu | 2 +- .../sources/reviews/159485.xml.conllu | 2 +- .../sources/reviews/374604.xml.conllu | 6 ++-- ...60511134300_ENG_20060511_134300.xml.conllu | 2 +- 7 files changed, 32 insertions(+), 32 deletions(-) diff --git a/en_ewt-ud-train.conllu b/en_ewt-ud-train.conllu index 1ee67dba2..3a7accdb1 100644 --- a/en_ewt-ud-train.conllu +++ b/en_ewt-ud-train.conllu @@ -24838,7 +24838,7 @@ 9 , , PUNCT , _ 12 punct 12:punct _ 10 both both DET DT PronType=Tot 12 nsubj 12:nsubj _ 11 just just ADV RB _ 12 advmod 12:advmod _ -12 16 16 NUM CD NumForm=Digit|NumType=Card 4 amod 4:amod SpaceAfter=No +12 16 16 NUM CD NumForm=Digit|NumType=Card 4 acl 4:acl SpaceAfter=No 13 , , PUNCT , _ 4 punct 4:punct _ 14 disappeared disappear VERB VBD Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin 0 root 0:root SpaceAfter=No 15 . . PUNCT . _ 14 punct 14:punct _ @@ -126607,7 +126607,7 @@ 17 _ _ PUNCT NFP _ 20 punct 20:punct SpaceAfter=No 18 St. St. PROPN NNP Number=Sing 20 nsubj 20:nsubj CorrectSpaceAfter=Yes|SpaceAfter=No 19 George George PROPN NNP Number=Sing 18 flat 18:flat _ -20 Fighting fight VERB VBG VerbForm=Ger 16 obj 16:obj _ +20 Fighting fight VERB VBG ExtPos=PROPN|VerbForm=Ger 16 obj 16:obj _ 21 the the DET DT Definite=Def|PronType=Art 22 det 22:det _ 22 Dragon Dragon PROPN NNP Number=Sing 20 obj 20:obj SpaceAfter=No 23 _ _ PUNCT NFP _ 25 punct 25:punct _ @@ -159214,13 +159214,13 @@ # newpar id = answers-20111108094927AA5NjHj_ans-p0002 # text = Im around 5'2 - 5'4 , 11 years old and im wondering what size horse i'll need that i wont grow out of quickly? 1-2 Im _ _ _ _ _ _ _ _ -1 I I PRON PRP Case=Nom|Number=Sing|Person=1|PronType=Prs 4 nsubj 4:nsubj _ -2 m be AUX VBP Mood=Ind|Number=Sing|Person=1|Tense=Pres|Typo=Yes|VerbForm=Fin 4 cop 4:cop CorrectForm='m -3 around around ADV RB _ 4 advmod 4:advmod _ +1 I I PRON PRP Case=Nom|Number=Sing|Person=1|PronType=Prs 5 nsubj 5:nsubj _ +2 m be AUX VBP Mood=Ind|Number=Sing|Person=1|Tense=Pres|Typo=Yes|VerbForm=Fin 5 cop 5:cop CorrectForm='m +3 around around ADV RB _ 5 advmod 5:advmod _ 4 5 5 NUM CD NumForm=Digit|NumType=Card 5 nummod 5:nummod SpaceAfter=No 5 ' ' NOUN NNS Number=Plur 0 root 0:root SpaceAfter=No 6 2 2 NUM CD NumForm=Digit|NumType=Card 5 compound 5:compound _ -7 - - SYM SYM _ 8 case 8:case _ +7 - - SYM SYM _ 9 case 9:case _ 8 5 5 NUM CD NumForm=Digit|NumType=Card 9 nummod 9:nummod SpaceAfter=No 9 ' ' NOUN NNS Number=Plur 5 nmod 5:nmod:to SpaceAfter=No 10 4 4 NUM CD NumForm=Digit|NumType=Card 9 compound 9:compound _ @@ -159344,14 +159344,14 @@ 6 I I PRON PRP Case=Nom|Number=Sing|Person=1|PronType=Prs 8 nsubj 8:nsubj _ 7 was be AUX VBD Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin 8 cop 8:cop _ 8 12 12 NUM CD NumForm=Digit|NumType=Card 2 advcl 2:advcl:when _ -9 and and CCONJ CC _ 13 cc 13:cc _ -10 I I PRON PRP Case=Nom|Number=Sing|Person=1|PronType=Prs 13 nsubj 13:nsubj _ -11 was be AUX VBD Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin 13 cop 13:cop _ -12 already already ADV RB _ 13 advmod 13:advmod _ +9 and and CCONJ CC _ 14 cc 14:cc _ +10 I I PRON PRP Case=Nom|Number=Sing|Person=1|PronType=Prs 14 nsubj 14:nsubj _ +11 was be AUX VBD Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin 14 cop 14:cop _ +12 already already ADV RB _ 14 advmod 14:advmod _ 13 5 5 NUM CD NumForm=Digit|NumType=Card 14 nummod 14:nummod SpaceAfter=No 14 ' ' NOUN NNS Number=Plur 2 conj 2:conj:and SpaceAfter=No 15 9 9 NUM CD NumForm=Digit|NumType=Card 14 compound 14:compound SpaceAfter=No -16 - - SYM SYM _ 17 case 17:case SpaceAfter=No +16 - - SYM SYM _ 18 case 18:case SpaceAfter=No 17 5 5 NUM CD NumForm=Digit|NumType=Card 18 nummod 18:nummod SpaceAfter=No 18 ' ' NOUN NNS Number=Plur 14 nmod 14:nmod:to SpaceAfter=No 19 10 10 NUM CD NumForm=Digit|NumType=Card 18 compound 18:compound SpaceAfter=No @@ -195031,7 +195031,7 @@ 18 The the DET DT Definite=Def|PronType=Art 20 det 20:det _ 19 owner owner NOUN NN Number=Sing 20 compound 20:compound _ 20 operator operator NOUN NN Number=Sing 22 dislocated 22:dislocated _ -21 he he PRON PRP Case=Nom|Gender=Masc|Number=Sing|Person=3|PronType=Prs 20 nsubj 20:nsubj _ +21 he he PRON PRP Case=Nom|Gender=Masc|Number=Sing|Person=3|PronType=Prs 22 nsubj 22:nsubj _ 22 does do VERB VBZ Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin 8 parataxis 8:parataxis _ 23 all all DET PDT PronType=Tot 26 det:predet 26:det:predet _ 24 the the DET DT Definite=Def|PronType=Art 26 reparandum 26:reparandum _ @@ -209286,7 +209286,7 @@ 9-10 That's _ _ _ _ _ _ _ _ 9 That that PRON DT Number=Sing|PronType=Dem 11 nsubj 11:nsubj _ 10 's be AUX VBZ Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin 11 cop 11:cop _ -11 Amore Amore PROPN NNP Number=Sing 7 nmod 7:nmod:of SpaceAfter=No +11 Amore Amore PROPN NNP ExtPos=PROPN|Number=Sing 7 nmod 7:nmod:of SpaceAfter=No 12 . . PUNCT . _ 7 punct 7:punct _ # sent_id = reviews-135010-0005 @@ -210327,9 +210327,9 @@ 6 like like ADP IN _ 7 case 7:case _ 7 that that PRON DT Number=Sing|PronType=Dem 4 obl 4:obl:like _ 8 regardless regardless ADV RB _ 4 advmod 4:advmod _ -9 of of ADP IN _ 11 case 11:case _ +9 of of ADP IN _ 11 mark 11:mark _ 10 how how ADV WRB PronType=Int 11 advmod 11:advmod _ -11 bad bad ADJ JJ Degree=Pos 8 obl 8:obl:of _ +11 bad bad ADJ JJ Degree=Pos 8 advcl 8:advcl:of _ 12 their their PRON PRP$ Case=Gen|Number=Plur|Person=3|Poss=Yes|PronType=Prs 13 nmod:poss 13:nmod:poss _ 13 day day NOUN NN Number=Sing 11 nsubj 11:nsubj _ 14 may may AUX MD VerbForm=Fin 11 aux 11:aux _ @@ -210339,7 +210339,7 @@ 18 what what PRON WP PronType=Int 21 nsubj 21:nsubj _ 19 may may AUX MD VerbForm=Fin 21 aux 21:aux _ 20 be be AUX VB VerbForm=Inf 21 aux 21:aux _ -21 going go VERB VBG Tense=Pres|VerbForm=Part 11 conj 11:conj:or _ +21 going go VERB VBG Tense=Pres|VerbForm=Part 11 conj 8:advcl:of|11:conj:or _ 22 on on ADP RP _ 21 compound:prt 21:compound:prt _ 23 in in ADP IN _ 26 case 26:case _ 24 their their PRON PRP$ Case=Gen|Number=Plur|Person=3|Poss=Yes|PronType=Prs 26 nmod:poss 26:nmod:poss _ diff --git a/not-to-release/sources/answers/20111108094927AA5NjHj_ans.xml.conllu b/not-to-release/sources/answers/20111108094927AA5NjHj_ans.xml.conllu index d6781d7e2..da082f430 100644 --- a/not-to-release/sources/answers/20111108094927AA5NjHj_ans.xml.conllu +++ b/not-to-release/sources/answers/20111108094927AA5NjHj_ans.xml.conllu @@ -19,13 +19,13 @@ # newpar id = answers-20111108094927AA5NjHj_ans-p0002 # text = Im around 5'2 - 5'4 , 11 years old and im wondering what size horse i'll need that i wont grow out of quickly? 1-2 Im _ _ _ _ _ _ _ _ -1 I I PRON PRP Case=Nom|Number=Sing|Person=1|PronType=Prs 4 nsubj 4:nsubj _ -2 m be AUX VBP Mood=Ind|Number=Sing|Person=1|Tense=Pres|Typo=Yes|VerbForm=Fin 4 cop 4:cop CorrectForm='m -3 around around ADV RB _ 4 advmod 4:advmod _ +1 I I PRON PRP Case=Nom|Number=Sing|Person=1|PronType=Prs 5 nsubj 5:nsubj _ +2 m be AUX VBP Mood=Ind|Number=Sing|Person=1|Tense=Pres|Typo=Yes|VerbForm=Fin 5 cop 5:cop CorrectForm='m +3 around around ADV RB _ 5 advmod 5:advmod _ 4 5 5 NUM CD NumForm=Digit|NumType=Card 5 nummod 5:nummod SpaceAfter=No 5 ' ' NOUN NNS Number=Plur 0 root 0:root SpaceAfter=No 6 2 2 NUM CD NumForm=Digit|NumType=Card 5 compound 5:compound _ -7 - - SYM SYM _ 8 case 8:case _ +7 - - SYM SYM _ 9 case 9:case _ 8 5 5 NUM CD NumForm=Digit|NumType=Card 9 nummod 9:nummod SpaceAfter=No 9 ' ' NOUN NNS Number=Plur 5 nmod 5:nmod:to SpaceAfter=No 10 4 4 NUM CD NumForm=Digit|NumType=Card 9 compound 9:compound _ @@ -149,14 +149,14 @@ 6 I I PRON PRP Case=Nom|Number=Sing|Person=1|PronType=Prs 8 nsubj 8:nsubj _ 7 was be AUX VBD Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin 8 cop 8:cop _ 8 12 12 NUM CD NumForm=Digit|NumType=Card 2 advcl 2:advcl:when _ -9 and and CCONJ CC _ 13 cc 13:cc _ -10 I I PRON PRP Case=Nom|Number=Sing|Person=1|PronType=Prs 13 nsubj 13:nsubj _ -11 was be AUX VBD Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin 13 cop 13:cop _ -12 already already ADV RB _ 13 advmod 13:advmod _ +9 and and CCONJ CC _ 14 cc 14:cc _ +10 I I PRON PRP Case=Nom|Number=Sing|Person=1|PronType=Prs 14 nsubj 14:nsubj _ +11 was be AUX VBD Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin 14 cop 14:cop _ +12 already already ADV RB _ 14 advmod 14:advmod _ 13 5 5 NUM CD NumForm=Digit|NumType=Card 14 nummod 14:nummod SpaceAfter=No 14 ' ' NOUN NNS Number=Plur 2 conj 2:conj:and SpaceAfter=No 15 9 9 NUM CD NumForm=Digit|NumType=Card 14 compound 14:compound SpaceAfter=No -16 - - SYM SYM _ 17 case 17:case SpaceAfter=No +16 - - SYM SYM _ 18 case 18:case SpaceAfter=No 17 5 5 NUM CD NumForm=Digit|NumType=Card 18 nummod 18:nummod SpaceAfter=No 18 ' ' NOUN NNS Number=Plur 14 nmod 14:nmod:to SpaceAfter=No 19 10 10 NUM CD NumForm=Digit|NumType=Card 18 compound 18:compound SpaceAfter=No diff --git a/not-to-release/sources/newsgroup/groups.google.com_humanities.lit.authors.shakespeare_0018a7697318f71f_ENG_20031006_163200.xml.conllu b/not-to-release/sources/newsgroup/groups.google.com_humanities.lit.authors.shakespeare_0018a7697318f71f_ENG_20031006_163200.xml.conllu index 34704df9d..758caf848 100644 --- a/not-to-release/sources/newsgroup/groups.google.com_humanities.lit.authors.shakespeare_0018a7697318f71f_ENG_20031006_163200.xml.conllu +++ b/not-to-release/sources/newsgroup/groups.google.com_humanities.lit.authors.shakespeare_0018a7697318f71f_ENG_20031006_163200.xml.conllu @@ -25,7 +25,7 @@ 17 _ _ PUNCT NFP _ 20 punct 20:punct SpaceAfter=No 18 St. St. PROPN NNP Number=Sing 20 nsubj 20:nsubj CorrectSpaceAfter=Yes|SpaceAfter=No 19 George George PROPN NNP Number=Sing 18 flat 18:flat _ -20 Fighting fight VERB VBG VerbForm=Ger 16 obj 16:obj _ +20 Fighting fight VERB VBG ExtPos=PROPN|VerbForm=Ger 16 obj 16:obj _ 21 the the DET DT Definite=Def|PronType=Art 22 det 22:det _ 22 Dragon Dragon PROPN NNP Number=Sing 20 obj 20:obj SpaceAfter=No 23 _ _ PUNCT NFP _ 25 punct 25:punct _ diff --git a/not-to-release/sources/reviews/135010.xml.conllu b/not-to-release/sources/reviews/135010.xml.conllu index 02f4527d9..099b2893f 100644 --- a/not-to-release/sources/reviews/135010.xml.conllu +++ b/not-to-release/sources/reviews/135010.xml.conllu @@ -42,7 +42,7 @@ 9-10 That's _ _ _ _ _ _ _ _ 9 That that PRON DT Number=Sing|PronType=Dem 11 nsubj 11:nsubj _ 10 's be AUX VBZ Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin 11 cop 11:cop _ -11 Amore Amore PROPN NNP Number=Sing 7 nmod 7:nmod:of SpaceAfter=No +11 Amore Amore PROPN NNP ExtPos=PROPN|Number=Sing 7 nmod 7:nmod:of SpaceAfter=No 12 . . PUNCT . _ 7 punct 7:punct _ # sent_id = reviews-135010-0005 diff --git a/not-to-release/sources/reviews/159485.xml.conllu b/not-to-release/sources/reviews/159485.xml.conllu index 9d1fcf12e..80c8aa4c7 100644 --- a/not-to-release/sources/reviews/159485.xml.conllu +++ b/not-to-release/sources/reviews/159485.xml.conllu @@ -22,7 +22,7 @@ 18 The the DET DT Definite=Def|PronType=Art 20 det 20:det _ 19 owner owner NOUN NN Number=Sing 20 compound 20:compound _ 20 operator operator NOUN NN Number=Sing 22 dislocated 22:dislocated _ -21 he he PRON PRP Case=Nom|Gender=Masc|Number=Sing|Person=3|PronType=Prs 20 nsubj 20:nsubj _ +21 he he PRON PRP Case=Nom|Gender=Masc|Number=Sing|Person=3|PronType=Prs 22 nsubj 22:nsubj _ 22 does do VERB VBZ Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin 8 parataxis 8:parataxis _ 23 all all DET PDT PronType=Tot 26 det:predet 26:det:predet _ 24 the the DET DT Definite=Def|PronType=Art 26 reparandum 26:reparandum _ diff --git a/not-to-release/sources/reviews/374604.xml.conllu b/not-to-release/sources/reviews/374604.xml.conllu index 56d9384a9..4386fd156 100644 --- a/not-to-release/sources/reviews/374604.xml.conllu +++ b/not-to-release/sources/reviews/374604.xml.conllu @@ -91,9 +91,9 @@ 6 like like ADP IN _ 7 case 7:case _ 7 that that PRON DT Number=Sing|PronType=Dem 4 obl 4:obl:like _ 8 regardless regardless ADV RB _ 4 advmod 4:advmod _ -9 of of ADP IN _ 11 case 11:case _ +9 of of ADP IN _ 11 mark 11:mark _ 10 how how ADV WRB PronType=Int 11 advmod 11:advmod _ -11 bad bad ADJ JJ Degree=Pos 8 obl 8:obl:of _ +11 bad bad ADJ JJ Degree=Pos 8 advcl 8:advcl:of _ 12 their their PRON PRP$ Case=Gen|Number=Plur|Person=3|Poss=Yes|PronType=Prs 13 nmod:poss 13:nmod:poss _ 13 day day NOUN NN Number=Sing 11 nsubj 11:nsubj _ 14 may may AUX MD VerbForm=Fin 11 aux 11:aux _ @@ -103,7 +103,7 @@ 18 what what PRON WP PronType=Int 21 nsubj 21:nsubj _ 19 may may AUX MD VerbForm=Fin 21 aux 21:aux _ 20 be be AUX VB VerbForm=Inf 21 aux 21:aux _ -21 going go VERB VBG Tense=Pres|VerbForm=Part 11 conj 11:conj:or _ +21 going go VERB VBG Tense=Pres|VerbForm=Part 11 conj 8:advcl:of|11:conj:or _ 22 on on ADP RP _ 21 compound:prt 21:compound:prt _ 23 in in ADP IN _ 26 case 26:case _ 24 their their PRON PRP$ Case=Gen|Number=Plur|Person=3|Poss=Yes|PronType=Prs 26 nmod:poss 26:nmod:poss _ diff --git a/not-to-release/sources/weblog/blogspot.com_rigorousintuition_20060511134300_ENG_20060511_134300.xml.conllu b/not-to-release/sources/weblog/blogspot.com_rigorousintuition_20060511134300_ENG_20060511_134300.xml.conllu index 7c84ac115..e26316e11 100644 --- a/not-to-release/sources/weblog/blogspot.com_rigorousintuition_20060511134300_ENG_20060511_134300.xml.conllu +++ b/not-to-release/sources/weblog/blogspot.com_rigorousintuition_20060511134300_ENG_20060511_134300.xml.conllu @@ -3956,7 +3956,7 @@ 9 , , PUNCT , _ 12 punct 12:punct _ 10 both both DET DT PronType=Tot 12 nsubj 12:nsubj _ 11 just just ADV RB _ 12 advmod 12:advmod _ -12 16 16 NUM CD NumForm=Digit|NumType=Card 4 amod 4:amod SpaceAfter=No +12 16 16 NUM CD NumForm=Digit|NumType=Card 4 acl 4:acl SpaceAfter=No 13 , , PUNCT , _ 4 punct 4:punct _ 14 disappeared disappear VERB VBD Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin 0 root 0:root SpaceAfter=No 15 . . PUNCT . _ 14 punct 14:punct _