Location for grammar source files

svn/trunk@7122

examples/grammars/basque_grammars/basque1.cfg

@@ -0,0 +1,11 @@
+	P -> IS	AS
+	AS -> IS ADI
+	AS -> ADI
+	IS -> IM erl_atz
+	IM -> ize_arr
+	IM -> ize_izb
+	ADI -> adt
+	erl_atz -> "k" | "a"
+	ize_arr -> "ardo" | "egunkari" | "baloi"
+	ize_izb -> "Pintxo" | "Kepa" 
+	adt -> "dakar" | "darama"

examples/grammars/basque_grammars/basque1.fcfg

@@ -0,0 +1,22 @@
+% start AS
+# ############################
+# Grammar Rules
+# ############################
+# AS expansion rules
+AS[ergnum=?n1, absnum=?n2] -> IS[kas=erg, num=?n1] AS[ergnum=?n1, absnum=?n2]
+AS[ergnum=?n1, absnum=?n2] -> AS[ergnum=?n1, absnum=?n2] IS[kas=erg, num=?n1] 
+AS[ergnum=?n1, absnum=?n2] -> IS[kas=abs, num=?n2] AS[ergnum=?n1, absnum=?n2]
+AS[ergnum=?n1, absnum=?n2] -> AS[ergnum=?n1, absnum=?n2] IS[kas=abs, num=?n2] 
+IS[kas=?k, num=?n] -> ize[azp=arr] knmdek[kas=?k, num=?n]
+AS[ergnum=?n1, absnum=?n2] -> adt[ergnum=?n1, absnum=?n2]
+# ############################
+# Lexicon
+# ############################
+adt[ergnum=hu, absnum=hu] -> 'dakar' | 'darama'
+adt[ergnum=hk, absnum=hu] -> 'dakarte' | 'daramate'
+knmdek[kas=erg, num=hu] -> 'ak'
+knmdek[kas=erg, num=hk] -> 'ek'
+knmdek[kas=abs, num=hk] -> 'ak'
+knmdek[kas=abs, num=hu] -> 'a'
+ize[azp=arr] -> 'zakur' | 'gizon'
+

examples/grammars/basque_grammars/basque1.pcfg

@@ -0,0 +1,21 @@
+	as -> mendekoa as [0.15]
+	as -> adlg mendekoa as [0.31]
+	as -> adlg adlg mendekoa as [0.08]
+	as -> adi adl [0.46]
+	mendekoa -> adlg mendekoa [0.37]
+	mendekoa -> adlg adlg mendekoa [0.09]
+	mendekoa -> 'joatea' [0.18]
+	mendekoa -> 'joateko' [0.27]
+	mendekoa -> 'sartzera' [0.09]
+	adi -> 'esan' [0.5]
+	adi -> 'debekatzen' [0.33]
+	adi -> 'eraman' [0.17]
+	adl -> 'zuen' [0.17]
+	adl -> 'zioten' [0.83]
+	adlg -> 'bozgorailuarekin' [0.28]
+	adlg -> 'euskal_presoekin' [0.18]
+	adlg -> 'epaitegian' [0.09]
+	adlg -> 'mendira' [0.18]
+	adlg -> 'ejertzitoan' [0.09]
+	adlg -> 'derrigorrean' [0.09]
+	adlg -> 'lagunekin' [0.09]

examples/grammars/basque_grammars/basque1.regexp

@@ -0,0 +1 @@
+NP: {<IZE.*>+<ADJ.*>*<DET.*>*} """ # adjetibo edo determinatzaileei loturiko izenak nahiz izen segidak topatzen ditu

examples/grammars/basque_grammars/basque2.cfg

@@ -0,0 +1,10 @@
+	S -> is as
+	is -> ize adj | ior
+	ize -> 'gaizkile' | 'epaile' | 'bizilagun'
+	adj -> 'gaiztoek' | 'gaiztoak' | 'kanpotarrak' | 'kanpotarrek' | 'berriak' | 'berriek'
+	ior -> 'haiek' | 'hark'
+	as -> mendekoa as | adlg mendekoa as | adlg adlg mendekoa as | adi adl
+	mendekoa -> adlg mendekoa | adlg adlg mendekoa | 'joatea' | 'joateko' | 'sartzera'
+	adi -> 'esan' | 'debekatzen' | 'eraman'
+	adl -> 'zuen' |'zioten' 
+	adlg -> 'bozgorailuarekin' | 'euskal_presoekin' | 'epaitegian' | 'mendira' | 'ejertzitoan' | 'derrigorrean' | 'lagunekin'

examples/grammars/basque_grammars/basque2.fcfg

@@ -0,0 +1,26 @@
+% start S
+# ############################
+# Grammar Rules
+# ############################
+S -> IS[kas=erg] AS/IS
+# IS erregelak
+IS[kas=?k, num=?n] -> ize[azp=arr] knmdek[kas=?k, num=?n]
+IS[kas=?k, num=?n] -> ize[azp=ber] knmdek[kas=?k, num=?n]
+IS[kas=?k, num=?n]/IS ->
+# AS erregelak
+AS[ergnum=?n1, absnum=?n2]/?x -> IS[kas=abs, num=?n1]/?x AS[ergnum=?n1, absnum=?n2]
+AS[ergnum=?n1, absnum=?n2] -> adi adl[ergnum=?n1, absnum=?n2]
+# ############################
+# Lexicon
+# ############################
+knmdek[kas=erg, num=hu] -> 'ak'
+knmdek[kas=erg, num=hk] -> 'ek'
+knmdek[kas=abs, num=hk] -> 'ak'
+knmdek[kas=abs, num=hu] -> 'a'
+ize[azp=arr] -> 'bizilagun' | 'aita' | 'gizon' | 'emakume'
+ize[azp=ber] -> 'Kepa' | 'Ainara'
+adi -> 'ekarri' | 'eraman' | 'puskatu' | 'lapurtu'
+adl[ergnum=hu, absnum=hu]  -> 'du'      | 'zuen'
+adl[ergnum=hk, absnum=hu]  -> 'dute'    | 'zuten'
+adl[ergnum=hu, absnum=hk]  -> 'ditu'    | 'zituen'
+adl[ergnum=hk, absnum=hk]  -> 'dituzte' | 'zituzten'

examples/grammars/basque_grammars/basque2.pcfg

@@ -0,0 +1,4 @@
+	IS -> IZE_ARR [0.5] | IZE_ARR ADJ [0.3] | IS LOT IS [0.2]
+	IZE_ARR -> 'gizon' [0.1] | 'emakume' [0.2] | 'ume' [0.3] | IZE_ARR LOT IZE_ARR [0.4]
+	ADJ -> 'zaharrak' [0.4] | 'gazteak' [0.6] 
+	LOT -> 'eta' [0.9] | 'edo' [0.1]

examples/grammars/basque_grammars/basque2.regexp

@@ -0,0 +1,2 @@
+	NP: {<IZE.*><ADJ.*>*<DET.*>*} # adjetibo edo determinatzaileei loturiko izenak topatzen ditu
+	NP: {<IZE.*>+} # izen segidak topatzen ditu

examples/grammars/basque_grammars/basque3.cfg

@@ -0,0 +1,4 @@
+	IS -> IZE_ARR | IZE_ARR ADJ | IS LOT IS
+	IZE_ARR -> 'gizon' | 'emakume' | 'ume' | IZE_ARR LOT IZE_ARR
+	ADJ -> 'zaharrak' | 'gazteak' 
+	LOT -> 'eta' | 'edo'

examples/grammars/basque_grammars/basque3.fcfg

@@ -0,0 +1,36 @@
+% start S
+# ############################
+# Grammar Rules
+# ############################
+
+## NORK-NOR Kasuak
+
+S -> IS[kas=erg] AS/IS
+# IS erregelak
+IS[kas=?k, num=?n] -> ize[azp=arr] knmdek[kas=?k, num=?n]
+IS[kas=?k, num=?n] -> ize[azp=ber] knmdek[kas=?k, num=?n]
+
+IS[kas=?k, num=?n]/IS ->
+
+# AS erregelak
+AS[ergnum=?n1, absnum=?n2]/?x -> IS[kas=abs, num=?n1]/?x AS[ergnum=?n1, absnum=?n2]
+AS[ergnum=?n1, absnum=?n2] -> adi adl[ergnum=?n1, absnum=?n2]
+# ############################
+# Lexicon
+# ############################
+
+knmdek[kas=erg, num=hu] -> 'ak'
+knmdek[kas=erg, num=hk] -> 'ek'
+
+knmdek[kas=abs, num=hk] -> 'ak'
+knmdek[kas=abs, num=hu] -> 'a'
+
+ize[azp=arr] -> 'bizilagun' | 'aita' | 'gizon' | 'emakume'
+ize[azp=ber] -> 'Kepa' | 'Ainara'
+
+adi -> 'ekarri' | 'eraman' | 'puskatu' | 'lapurtu'
+
+adl[ergnum=hu, absnum=hu]  -> 'du'      | 'zuen'
+adl[ergnum=hk, absnum=hu]  -> 'dute'    | 'zuten'
+adl[ergnum=hu, absnum=hk]  -> 'ditu'    | 'zituen'
+adl[ergnum=hk, absnum=hk]  -> 'dituzte' | 'zituzten'

examples/grammars/basque_grammars/basque3.regexp

@@ -0,0 +1,3 @@
+IS:
+     {<.*>+}           # Edozer Onartzen Duen Chunkerra
+     }<ADI.*|ADL.*|ADT.*|PUNT.*|POST.*|LOT.*|ADB.*>+{      # Chink Bezala Barneratu Aditzak (ADI.*, ADT.* eta ADL.*), Adberbioak (ADB.*), Preposizioak (POST.*), Loturak (LOT.*) Eta Puntuazio Ikurrak (PUNT.*)

examples/grammars/basque_grammars/basque4.regexp

@@ -0,0 +1,3 @@
+  IS: {(<ADJ.*>*<DET.*>*<IZE.*>+<ADJ.*>*<DET.*>*)*} #noun phrase chunks
+  AS: {(<ADI.*|ADL.*|ADT.*>*)+} # verb phrase chunks
+  PS: {<POST.*>+} # prepositional phrase chunks

examples/grammars/basque_grammars/basque5.regexp

@@ -0,0 +1,5 @@
+  IS: {(<ADJ.*>*<DET.*>*<IZE.*>*<ADJ.*>*<DET.*>*)*} #noun phrase chunks
+  AS: {(<ADI.*|ADL.*|ADT.*>+)+<POST.*>*}            # verb phrase chunks
+  PS: {<POST.*>+} 				    # prepositional phrase chunks
+  S:  {<IS><AS>}
+      {<AS><IS>}				    # Chunk NP, VP

examples/grammars/book_grammars/drt.fcfg

@@ -0,0 +1,82 @@
+## Natural Language Toolkit: drt.fcfg
+## 
+## Author: Dan Garrette <[email protected]> 
+## URL: <http://www.nltk.orgt>
+## For license information, see LICENSE.TXT
+
+% start S
+############################
+# Grammar Rules
+#############################
+
+S[sem = <app(?subj,?vp)>] -> NP[num=?n,sem=?subj] VP[num=?n,sem=?vp]
+
+NP[num=?n,sem=<app(?det,?nom)> ] -> Det[num=?n,sem=?det]  Nom[num=?n,sem=?nom]
+NP[loc=?l,num=?n,sem=?np] -> PropN[loc=?l,num=?n,sem=?np]
+
+Nom[num=?n,sem=?nom] -> N[num=?n,sem=?nom]
+Nom[num=?n,sem=<app(?pp,?nom)>] -> N[num=?n,sem=?nom] PP[sem=?pp]
+
+VP[num=?n,sem=?v] -> IV[num=?n,sem=?v]
+VP[num=?n,sem=<app(?v,?obj)>] -> TV[num=?n,sem=?v] NP[sem=?obj]
+
+#############################
+# Lexical Rules
+#############################
+
+PropN[-loc,num=sg,sem=<\P.(DRS([x],[Angus(x)])+P(x))>] -> 'Angus'
+PropN[-loc,num=sg,sem=<\P.(DRS([x],[Irene(x)])+P(x))>] -> 'Irene'
+PropN[-loc,num=sg,sem=<\P.(DRS([x],[John(x)])+P(x))>] -> 'John'
+PropN[-loc,num=sg,sem=<\P.(DRS([x],[Mary(x)])+P(x))>] -> 'Mary'
+PropN[-loc,num=sg,sem=<\P.(DRS([x],[Suzie(x)])+P(x))>] -> 'Suzie'
+PropN[-loc,num=sg,sem=<\P.(DRS([x],[Vincent(x)])+P(x))>] -> 'Vincent'
+PropN[-loc,num=sg,sem=<\P.(DRS([x],[Mia(x)])+P(x))>] -> 'Mia'
+PropN[-loc,num=sg,sem=<\P.(DRS([x],[Marsellus(x)])+P(x))>] -> 'Marsellus'
+PropN[-loc,num=sg,sem=<\P.(DRS([x],[Fido(x)])+P(x))>] -> 'Fido'
+PropN[+loc,num=sg,sem=<\P.(DRS([x],[Noosa(x)])+P(x))>] -> 'Noosa'
+PropN[-loc,num=sg,sem=<\P.(DRS([x],[PRO(x)])+P(x))>] -> 'he'
+PropN[-loc,num=sg,sem=<\P.(DRS([x],[PRO(x)])+P(x))>] -> 'she'
+PropN[-loc,num=sg,sem=<\P.(DRS([x],[PRO(x)])+P(x))>] -> 'it'
+
+Det[num=sg,sem=<\P Q.DRS([],[((DRS([x],[])+P(x)) implies Q(x))])>] -> 'every' | 'Every' 
+Det[num=pl,sem=<\P Q.DRS([],[((DRS([x],[])+P(x)) implies Q(x))])>] -> 'all' | 'All'
+Det[sem=<\P Q.((DRS([x],[])+P(x))+Q(x))>] -> 'some' | 'Some'
+Det[num=sg,sem=<\P Q.((DRS([x],[])+P(x))+Q(x))>] -> 'a' | 'A'
+Det[num=sg,sem=<\P Q.(not ((DRS([x],[])+P(x))+Q(x)))>] -> 'no' | 'No'
+
+N[num=sg,sem=<\x.DRS([],[boy(x)])>] -> 'boy'
+N[num=pl,sem=<\x.DRS([],[boy(x)])>] -> 'boys' 
+N[num=sg,sem=<\x.DRS([],[girl(x)])>] -> 'girl'
+N[num=pl,sem=<\x.DRS([],[girl(x)])>] -> 'girls'
+N[num=sg,sem=<\x.DRS([],[dog(x)])>] -> 'dog'
+N[num=pl,sem=<\x.DRS([],[dog(x)])>] -> 'dogs'
+N[num=sg,sem=<\x.DRS([],[student(x)])>] -> 'student'
+N[num=pl,sem=<\x.DRS([],[student(x)])>] -> 'students'
+N[num=sg,sem=<\x.DRS([],[person(x)])>] -> 'person'
+N[num=pl,sem=<\x.DRS([],[person(x)])>] -> 'persons'
+N[num=sg,sem=<\x.DRS([],[boxerdog(x)])>] -> 'boxer'
+N[num=pl,sem=<\x.DRS([],[boxerdog(x)])>] -> 'boxers'
+N[num=sg,sem=<\x.DRS([],[boxer(x)])>] -> 'boxer'
+N[num=pl,sem=<\x.DRS([],[boxer(x)])>] -> 'boxers'
+N[num=sg,sem=<\x.DRS([],[garden(x)])>] -> 'garden'
+N[num=sg,sem=<\x.DRS([],[kitchen(x)])>] -> 'kitchen'
+
+IV[num=sg,sem=<\x.DRS([],[bark(x)])>,tns=pres] -> 'barks'
+IV[num=pl,sem=<\x.DRS([],[bark(x)])>,tns=pres] -> 'bark'
+IV[num=sg,sem=<\x.DRS([],[walk(x)])>,tns=pres] -> 'walks'
+IV[num=pl,sem=<\x.DRS([],[walk(x)])>,tns=pres] -> 'walk'
+IV[num=pl,sem=<\x.DRS([],[dance(x)])>,tns=pres] -> 'dance'
+IV[num=sg,sem=<\x.DRS([],[dance(x)])>,tns=pres] -> 'dances'
+
+TV[num=sg,sem=<\X x. X(\y.DRS([],[own(x,y)]))>,tns=pres] -> 'owns'
+TV[num=pl,sem=<\X x. X(\y.DRS([],[own(x,y)]))>,tns=pres] -> 'own'
+TV[num=sg,sem=<\X x. X(\y.DRS([],[bite(x,y)]))>,tns=pres] -> 'bites'
+TV[num=pl,sem=<\X x. X(\y.DRS([],[bite(x,y)]))>,tns=pres] -> 'bite'
+TV[num=sg,sem=<\X x. X(\y.DRS([],[chase(x,y)]))>,tns=pres] -> 'chases'
+TV[num=pl,sem=<\X x. X(\y.DRS([],[chase(x,y)]))>,tns=pres] -> 'chase'
+TV[num=sg,sem=<\X x. X(\y.DRS([],[marry(x,y)]))>,tns=pres] -> 'marries'
+TV[num=pl,sem=<\X x. X(\y.DRS([],[marry(x,y)]))>,tns=pres] -> 'marry'
+TV[num=sg,sem=<\X x. X(\y.DRS([],[know(x,y)]))>,tns=pres] -> 'knows'
+TV[num=pl,sem=<\X x. X(\y.DRS([],[know(x,y)]))>,tns=pres] -> 'know'
+TV[num=sg,sem=<\X x. X(\y.DRS([],[see(x,y)]))>,tns=pres] -> 'sees'
+TV[num=pl,sem=<\X x. X(\y.DRS([],[see(x,y)]))>,tns=pres] -> 'see'

examples/grammars/book_grammars/feat0.fcfg

@@ -0,0 +1,51 @@
+## Natural Language Toolkit: feat0.fcfg
+##
+## First example of a feature-based grammar for English, illustrating
+## value-sharing of NUM and TENSE features.
+## Used in Feature-Based Grammars chapter.
+## 
+## Author: Ewan Klein <[email protected]> 
+## URL: <http://nltk.sourceforge.net>
+## For license information, see LICENSE.TXT
+##
+## $Id: feat0.cfg 4674 2007-06-14 08:55:32Z ehk $
+
+% start S
+# ############################
+# Grammar Rules
+# ############################
+
+# S expansion rules
+S -> NP[NUM=?n] VP[NUM=?n]
+
+# NP expansion rules
+NP[NUM=?n] -> N[NUM=?n] 
+NP[NUM=?n] -> PropN[NUM=?n] 
+NP[NUM=?n] -> Det[NUM=?n] N[NUM=?n]
+NP[NUM=pl] -> N[NUM=pl] 
+
+# VP expansion rules
+VP[TENSE=?t, NUM=?n] -> IV[TENSE=?t, NUM=?n]
+VP[TENSE=?t, NUM=?n] -> TV[TENSE=?t, NUM=?n] NP
+
+# ############################
+# Lexical Rules
+# ############################
+
+Det[NUM=sg] -> 'this' | 'every'
+Det[NUM=pl] -> 'these' | 'all'
+Det -> 'the' | 'some'
+
+PropN[NUM=sg]-> 'Kim' | 'Jody'
+
+N[NUM=sg] -> 'dog' | 'girl' | 'car' | 'child'
+N[NUM=pl] -> 'dogs' | 'girls' | 'cars' | 'children' 
+
+IV[TENSE=pres,  NUM=sg] -> 'disappears' | 'walks'
+TV[TENSE=pres, NUM=sg] -> 'sees' | 'likes'
+
+IV[TENSE=pres,  NUM=pl] -> 'disappear' | 'walk'
+TV[TENSE=pres, NUM=pl] -> 'see' | 'like'
+
+IV[TENSE=past, NUM=?n] -> 'disappeared' | 'walked'
+TV[TENSE=past, NUM=?n] -> 'saw' | 'liked'

examples/grammars/book_grammars/feat1.fcfg

@@ -0,0 +1,39 @@
+## Natural Language Toolkit: feat1.fcfg
+##
+## Second example of a feature-based grammar, illustrating
+## SUBCAT and slash features. Also introduces S-BAR and embedded
+## clauses.
+## Used in Feature-Based Grammars chapter.
+## 
+## Author: Ewan Klein <[email protected]> 
+## URL: <http://nltk.sourceforge.net>
+## For license information, see LICENSE.TXT
+##
+## $Id: feat1.cfg 4674 2007-06-14 08:55:32Z ehk $
+
+% start S
+# ############################
+# Grammar Rules
+# ############################
+S[-INV] -> NP  S/NP
+S[-INV]/?x -> NP VP/?x
+S[+INV]/?x -> V[+AUX] NP VP/?x
+S-BAR/?x -> Comp S[-INV]/?x
+
+NP/NP ->
+
+VP/?x -> V[SUBCAT=1, -AUX] NP/?x
+VP/?x -> V[SUBCAT=2, -AUX] S-BAR/?x
+VP/?x -> V[SUBCAT=3, +AUX] VP/?x
+
+# ############################
+# Lexical Rules
+# ############################
+V[SUBCAT=1, -AUX] -> 'see' | 'like'
+V[SUBCAT=2, -AUX] -> 'say' | 'claim'
+V[SUBCAT=3, +AUX] -> 'do' | 'can'
+
+NP[-WH] -> 'you' | 'children' | 'girls'
+NP[+WH] -> 'who'
+
+Comp -> 'that'