query language generalized and extended ; added README

3 files changed, 201 insertions, 88 deletions

diff --git a/examples/query/Query.gf b/examples/query/Query.gf
index 34f714b88..4687f6c06 100644
--- a/examples/query/Query.gf
+++ b/examples/query/Query.gf
@@ -10,8 +10,10 @@ cat
   Query ;   

   Answer ;

   Set ;      -- the set requested,      e.g. "all persons"

-  Relation ; -- something of something, e.g. "subregion of Bulgaria"

+  Interrogative ; -- interrog. pron.    e.g. "who" 

+  Function ; -- something of something, e.g. "subregion of Bulgaria"

   Kind ;     -- type of things,         e.g. "person"

+  Relation ; -- relation between things,e.g. "employed at"

   Property ; -- property of things,     e.g. "employed at Google"

   Individual ; -- one entity,           e.g. "Google"

   Name ;       -- person, company...    e.g. "Eric Schmidt"

@@ -22,13 +24,16 @@ fun
   MAnswer : Answer -> Move ;

  

   QSet    : Set  -> Query ;  -- (give me | what are | which are | ) (S | the names of S | S's names)

-  QWhere  : Set  -> Query ;  -- where are S

-  QWhat   : Kind -> Property -> Query ; -- what K P

-  QWho    : Property -> Query ; -- who P

-  QRel    : Relation -> Set -> Query ; -- what R does S have

-  QInfo   : Set  -> Query ;  -- (give me | ) (information about | all about) S

-  QCalled : Individual -> Query ; -- how is X (also | otherwise) (called | named | known) ;

-  QWhether : Answer -> Query ; -- is S P --- not in the corpus, but should be ??

+  QWhere     : Set  -> Query ;  -- where are S

+  QWhat      : Interrogative -> Property -> Query ; -- who P

+  QWhatWhat  : Interrogative -> Interrogative -> Relation -> Query ; -- who R what

+  QWhatWhere : Interrogative -> Relation -> Query ; -- who R where --- overgenerating

+  QRelWhere  : Set -> Relation -> Query ; -- where does S R --- overgenerating

+  QFun       : Function -> Set -> Query ; -- what R does S have

+  QFunPair   : Set -> Function -> Query ; -- S and their R's

+  QInfo      : Set  -> Query ;  -- (give me | ) (information about | all about) S

+  QCalled    : Individual -> Query ; -- how is X (also | otherwise) (called | named | known) ;

+  QWhether   : Answer -> Query ; -- is S P --- not in the corpus, but should be ??

 

   AKind  : Set  -> Kind     -> Answer ; -- S is a K

   AInd   : Set  -> Individual -> Answer ; -- S is I

@@ -36,7 +41,7 @@ fun
   AProp  : Set  -> Property -> Answer ; -- S is P

 

   SAll   : Kind -> Set ;  -- all Ks | the Ks

-  SRel   : Set  -> Relation -> Set ;  -- S's Rs

+  SFun   : Set  -> Function -> Set ;  -- S's Rs

   SOne   : Kind -> Set ;  -- one K

   SIndef : Kind -> Set ;  -- a K

   SDef   : Kind -> Set ;  -- the K

@@ -45,12 +50,16 @@ fun
   SInd   : Individual  -> Set ;  -- X

   SInds  : [Individual] -> Set ; -- X and Y

 

-  KRelSet  : Relation -> Set -> Kind ; -- R of S | S's R

-  KRelsSet : Relation -> Relation -> Set -> Kind ; -- R and Q of S

-  KRelKind : Kind -> Relation -> Set -> Kind ; -- K that is R of S

-  KRelPair : Kind -> Relation -> Kind ; -- S's with their R's

+  IWho   : Interrogative ; -- who

+  IWhat  : Interrogative ; -- what

+  IWhich : Kind -> Interrogative ; -- which K | what K | which Ks | what Ks

+

+  KFunSet  : Function -> Set -> Kind ; -- R of S | S's R

+  KFunsSet : Function -> Function -> Set -> Kind ; -- R and Q of S

+  KFunKind : Kind -> Function -> Set -> Kind ; -- K that is R of S

+  KFunPair : Kind -> Function -> Kind ; -- S's with their R's

   KProp    : Property -> Kind -> Kind ; -- P K | K that is P

-  KRel     : Relation -> Kind ; -- R ---??

+  KFun     : Function -> Kind ; -- R ---??

 

   IName    : Name -> Individual ;

 

@@ -59,6 +68,8 @@ fun
 

   PIs      : Individual -> Property ;

 

+  PRelation : Relation -> Set -> Property ;

+

 -- the test lexicon

 

 cat

@@ -68,32 +79,37 @@ fun
   NCountry : Country -> Name ;

   PCountry : Country -> Property ;

 

-  Located : Set -> Property ;

+  Located : Relation ;

 

-  In : Set -> Property ;

-  HaveTitleAt : JobTitle -> Set -> Property ;

-  HaveTitle : JobTitle -> Property ;

-  Employed : Set -> Property ;

+  In : Relation ;

+  HaveTitleAt : JobTitle -> Relation ;

+  EmployedAt : Set -> Relation ;

+  HaveTitle : Relation ;

+  Employed : Relation ;

 

   Named : Name -> Property ;

+

   Start : Name -> Property ;

 

   Organization : Kind ;

+  Company : Kind ;

   Place : Kind ;

   Person : Kind ;

 

-  Location : Relation ;

-  Region : Relation ;

-  Subregion : Relation ;

+  Location : Function ;

+  Region : Function ;

+  Subregion : Function ;

 

   USA : Country ;

   California : Country ;

   Bulgaria : Country ;

   OblastSofiya : Name ;

 

-  RName     : Relation ;

-  RNickname : Relation ;

-  RJobTitle : Relation ;

+  FName     : Function ;

+  FNickname : Function ;

+  FJobTitle : Function ;

+

+  SJobTitle : JobTitle -> Set ; -- a programmer

 

   CEO : JobTitle ;

   ChiefInformationOfficer : JobTitle ;

diff --git a/examples/query/QueryEng.gf b/examples/query/QueryEng.gf
index 8f0756e77..7ab5c2ef5 100644
--- a/examples/query/QueryEng.gf
+++ b/examples/query/QueryEng.gf
@@ -15,9 +15,11 @@ lincat
   Query = Utt ;
   Answer = Cl ; -- Utt ;
   Set = NP ;
-  Relation = {cn : CN ; prep : Prep} ;
+  Interrogative = IP ;
+  Function = {cn : CN ; prep : Prep} ;
   Kind = CN ;
   Property = {ap : AP ; vp : VP} ;
+  Relation = {ap : AP ; vp : VP ; prep : Prep} ;
   Individual = NP ;
   Name = NP ;
   [Individual] = [NP] ;
@@ -39,19 +41,34 @@ lin
     | mkUtt (mkQS (mkQCl (L.CompIP (L.IdetIP (mkIDet which_IQuant))) ss))
     | mkUtt ss ;
 
-  QWhat k p = 
-    mkUtt (mkQS (mkQCl (mkIP (what_IQuant | which_IQuant) (sgNum | plNum) k) p.vp)) ;
-  QWho p = mkUtt (mkQS (mkQCl whoSg_IP p.vp)) ;
-
   QWhere s = 
       mkUtt (mkQS (mkQCl where_IAdv s))
     | mkUtt (mkQS (mkQCl where_IAdv (mkCl s (mkA "located" | mkA "situated")))) ;
-  QRel r s = 
+  QWhat i p = mkUtt (mkQS (mkQCl i p.vp)) ;
+  QWhatWhat i j p = mkUtt (mkQS (QuestQVP i (AdvQVP p.vp (mkIAdv p.prep j)))) ;
+  QWhatWhere i p = mkUtt (mkQS (QuestQVP i (AdvQVP p.vp where_IAdv))) ;
+  QRelWhere s p = mkUtt (mkQS (mkQCl where_IAdv (mkCl s p.vp))) ;
+
+  QFun r s = 
       mkUtt 
-        (mkImp (mkVP give_V3 (mkNP and_Conj s (mkNP (mkQuant they_Pron) plNum r.cn)) (mkNP i_Pron)))
+        (mkImp (mkVP give_V3 
+          (mkNP and_Conj s (mkNP (mkQuant they_Pron) plNum r.cn)) (mkNP i_Pron)))
     | mkUtt (mkQS (mkQCl (mkIP what_IQuant plNum r.cn) s have_V2))
     | mkUtt (mkQS (mkQCl whatSg_IP 
         (mkClSlash (mkClSlash s have_V2) (mkAdv as_Prep (mkNP aPl_Det r.cn))))) ; 
+
+  QFunPair s f = 
+    let 
+     ss0 : NP = s 
+              | mkNP (mkNP thePl_Det L.name_N) (mkAdv possess_Prep s) ;
+     ss  : NP = mkNP and_Conj ss0 (mkNP (mkQuant they_Pron) plNum f.cn)
+              | mkNP ss0 (mkAdv with_Prep (mkNP (mkQuant they_Pron) plNum f.cn))
+    in 
+      mkUtt (mkImp (mkVP give_V3 ss (mkNP i_Pron)))
+    | mkUtt (mkQS (mkQCl (L.CompIP whatPl_IP) ss))
+    | mkUtt (mkQS (mkQCl (L.CompIP (L.IdetIP (mkIDet which_IQuant))) ss))
+    | mkUtt ss ;
+
   QInfo  s = 
     let
       info : NP = mkNP (all_NP | (mkNP information_N)) (mkAdv about_Prep s) ;
@@ -72,7 +89,7 @@ lin
   AProp s p = (mkCl s p.vp) ;
 
   SAll k = mkNP all_Predet (mkNP aPl_Det k) | mkNP thePl_Det k ;
-  SRel s r = mkNP (GenNP s) plNum r.cn | mkNP (GenNP s) sgNum r.cn ;
+  SFun s r = mkNP (GenNP s) plNum r.cn | mkNP (GenNP s) sgNum r.cn ;
   SOne k = mkNP n1_Numeral k ;
   SIndef k = mkNP a_Det k ;
   SDef k = mkNP the_Det k ;
@@ -81,20 +98,27 @@ lin
   SInd i = i ;
   SInds is = mkNP and_Conj is ;
 
-  KRelSet r s = 
+  IWhich k = 
+      mkIP what_IQuant  (sgNum | plNum) k
+    | mkIP which_IQuant (sgNum | plNum) k ;
+
+  IWho = whoSg_IP | whoPl_IP ;
+  IWhat = whatSg_IP | whatPl_IP ;
+
+  KFunSet r s = 
      mkCN r.cn (mkAdv r.prep s) ;
 
-  KRelsSet r q s = 
+  KFunsSet r q s = 
      mkCN (ConjCN and_Conj (BaseCN r.cn q.cn)) (mkAdv r.prep s) ;
 
-  KRelKind k r s = 
+  KFunKind k r s = 
     mkCN k (mkRS (mkRCl that_RP (mkVP (mkNP aPl_Det (mkCN r.cn (mkAdv r.prep s)))))) ;
   
-  KRelPair k r = mkCN k (mkAdv with_Prep (mkNP (mkQuant they_Pron) plNum r.cn)) ;
+  KFunPair k r = mkCN k (mkAdv with_Prep (mkNP (mkQuant they_Pron) plNum r.cn)) ;
   KProp p k = 
      mkCN p.ap k 
    | mkCN k (mkRS (mkRCl that_RP p.vp)) ;
-  KRel r = r.cn ;
+  KFun r = r.cn ;
 
   IName n = n ;
 
@@ -103,6 +127,11 @@ lin
 
   PIs i = propVP (mkVP i) ;
 
+  PRelation r s = {
+    ap = AdvAP r.ap (mkAdv r.prep s) ; 
+    vp = mkVP r.vp (mkAdv r.prep s)
+    } ;
+
   BaseIndividual = mkListNP ;
   ConsIndividual = mkListNP ;
 
@@ -125,7 +154,7 @@ oper
 -- lexical constructors
   mkName : Str -> NP = 
     \s -> mkNP (mkPN s) ;
-  mkRelation : Str -> {cn : CN ; prep : Prep} = 
+  mkFunction : Str -> {cn : CN ; prep : Prep} = 
     \s -> {cn = mkCN (mkN s) ; prep = possess_Prep} ;
 
   propAP : AP -> {ap : AP ; vp : VP} = \ap -> {
@@ -138,9 +167,22 @@ oper
     vp = vp
     } ;
 
+  relAP : AP -> Prep -> {ap : AP ; vp : VP ; prep : Prep} = \ap,p -> {
+    ap = ap ;
+    vp = mkVP ap ;
+    prep = p
+    } ;
+
+  relVP : VP -> Prep -> {ap : AP ; vp : VP ; prep : Prep} = \vp,p -> {
+    ap = PartVP vp ;
+    vp = vp ;
+    prep = p
+    } ;
+
   propCalled : NP -> {ap : AP ; vp : VP} = \i -> 
     propAP (mkAP (also_AdA | otherwise_AdA) (mkAP (mkA2 called_A []) i)) ;
 
+  noPrep : Prep = mkPrep [] ;
 
 -- lexicon
 
@@ -151,65 +193,63 @@ lin
   NCountry c = c.np ;
   PCountry c = propAP (mkAP c.a) ;
 
-  Located i = propAP (
-      mkAP (mkA2 (mkA "located") in_Prep) i
-    | mkAP (mkA2 (mkA "situated") in_Prep) i
-    ) ;
-
-  In i = propVP (mkVP (mkAdv in_Prep i)) ;
-
-  Employed i = propAP ( 
-      mkAP (mkA2 (mkA "employed") by8agent_Prep) i
-    | mkAP (mkA2 (mkA "paid") by8agent_Prep) i
-    | mkAP (mkA2 (mkA "active") at_Prep) i
-    | mkAP (mkA2 (mkA "professionally active") at_Prep) i
-    )
-   |
-    propVP (
-      mkVP (mkV2 (mkV "work") at_Prep) i
-    | mkVP (mkV2 (mkV "collaborate") in_Prep) i
-    ) ;
-
-  HaveTitle t = 
-    propAP (
-      mkAP (mkA2 (mkA "employed") as_Prep) (mkNP t)
-      )
-    |
-    propVP (
-      mkVP (mkNP a_Det t)
-    | mkVP (mkV2 (mkV "work") as_Prep) (mkNP t) 
---    | mkVP have_V2 (mkNP the_Det (mkCN (mkN2 (mkN "title")) (mkNP t))) 
-    ) ;
-
-  HaveTitleAt t i = 
-    propAP (
-      mkAP (mkA2 (mkA "employed") as_Prep) (mkNP (mkNP t) (mkAdv at_Prep i))
-      )
-    |
-    propVP (
-      mkVP (mkVP (mkNP a_Det t)) (mkAdv at_Prep i) 
-    | mkVP (mkVP (mkV2 (mkV "work") as_Prep) (mkNP t)) (mkAdv at_Prep i) 
---    | mkVP (mkVP have_V2 (mkNP the_Det (mkCN (mkN2 (mkN "title")) (mkNP t)))) 
---           (mkAdv at_Prep i)
-    ) ;
+  Located = 
+      relAP (mkAP (mkA "located")) in_Prep
+    | relAP (mkAP (mkA "situated")) in_Prep
+    ;
+
+  In = relVP UseCopula in_Prep ;
+
+  Employed = 
+      relAP (mkAP (mkA "employed")) by8agent_Prep
+    | relAP (mkAP (mkA "paid")) by8agent_Prep
+    | relAP (mkAP (mkA "active")) at_Prep
+    | relAP (mkAP (mkA "professionally active")) at_Prep
+    | relVP (mkVP (mkV "work")) at_Prep
+    | relVP (mkVP (mkV "collaborate")) in_Prep
+    ;
+
+  HaveTitle = 
+      relAP (mkAP (mkA "employed")) as_Prep
+    --- | relVP UseCopula noPrep
+    | relVP (mkVP (mkV "work")) as_Prep
+    | relVP (mkVP have_V2 (mkNP the_Det (mkCN (mkN2 (mkN "title"))))) possess_Prep
+    ;
+
+  EmployedAt s = 
+      relAP (mkAP (mkA2 (mkA "employed") at_Prep) s) as_Prep
+    | relAP (mkAP (mkA2 (mkA "employed") by8agent_Prep) s) as_Prep
+    | relVP (mkVP (mkV2 (mkV "work") at_Prep) s) as_Prep 
+    ;
+
+  HaveTitleAt t = 
+      relAP (mkAP (mkA2 (mkA "employed") as_Prep) (mkNP t)) at_Prep
+    | relAP (mkAP (mkA2 (mkA "employed") as_Prep) (mkNP t)) by8agent_Prep
+    | relVP (mkVP (mkNP a_Det t)) at_Prep
+    | relVP (mkVP (mkV2 (mkV "work") as_Prep) (mkNP t)) at_Prep 
+    | relVP (mkVP have_V2 (mkNP the_Det (mkCN (mkN2 (mkN "title")) (mkNP t)))) at_Prep 
+    ;
 
   Named n = propAP  (mkAP (mkA2 (mkA "named") []) n) ;
   Start n = propVP (mkVP (mkV2 "start" with_Prep) n) ;
 
   Organization = mkCN (mkN "organization") ;
+  Company = mkCN (mkN "company") ;
   Place = mkCN (mkN "place") ;
   Person = 
       mkCN (mkN "person" "people")
     | mkCN (mkN "person") ;
 
-  Location = mkRelation "location" ;
-  Region = mkRelation "region" ;
-  Subregion = mkRelation "subregion" | mkRelation "sub-region" ;
-  RName = mkRelation "name" ;
-  RNickname = mkRelation "nickname" ;
-  RJobTitle = mkRelation "job title" | mkRelation "job" | mkRelation "position" |
-    mkRelation "appointment" | mkRelation "job position" | mkRelation "mandate" |
-    mkRelation "title" ;
+  Location = mkFunction "location" ;
+  Region = mkFunction "region" ;
+  Subregion = mkFunction "subregion" | mkFunction "sub-region" ;
+  FName = mkFunction "name" ;
+  FNickname = mkFunction "nickname" ;
+  FJobTitle = mkFunction "job title" | mkFunction "job" | mkFunction "position" |
+    mkFunction "appointment" | mkFunction "job position" | mkFunction "mandate" |
+    mkFunction "title" | mkFunction "capacity" ;
+
+  SJobTitle t = mkNP a_Det t ;
 
   USA = mkCountry "USA" "American" ;
   Bulgaria = mkCountry "Bulgaria" "Bulgarian" ;
diff --git a/examples/query/README b/examples/query/README
new file mode 100644
index 000000000..81442cd01
--- /dev/null
+++ b/examples/query/README
@@ -0,0 +1,57 @@
+Copyright (c) 2010 Aarne Ranta, under LGPL(3).
+Part of MOLTO Project, WP 4.
+
+Query language, based on the corpus from Ontotext.
+
+Purpose: natural language queries to an ontology database.
+
+Work in progress: 
+- 19 June parsing 28% 160/562
+- 17 June 2010 first version, parsing under 10%
+
+
+The corpus contains misspellings and ungrammatical sentences; these will (mostly) not
+be covered by the grammar.
+
+Test:
+
+  -- start GF with the grammar; notice that lib/present/ must have latest Eng libraries,
+  -- which can be provided by 'runghc Make present lang api langs=Eng' in lib/src/
+  % gf QueryEng.gf
+  -- parse a sentence and see all variants
+  > "p "Bulgarian people working at Google" | l -all
+
+Regression test:
+
+  -- run the parser on the corpus
+  % gf QueryEng.gf <test.gfs > test.results8
+  -- compute the number of sentences not covered
+  % grep "no tree" test.results8 | wc
+
+
+Semantics: generic logical semantics, that could be mapped to many query languages.
+The denotations of the main categories are, assuming a domain of individuals:
+
+  Set ;           P(P(D)) (generalized quantifier) -- the set requested, e.g. "all persons"
+  Function ;      D -> P(D)   -- something of something, e.g. "subregion of Bulgaria"
+  Kind ;          P(D)        -- type of things,         e.g. "person"
+  Relation ;      D -> D -> T -- relation between things,e.g. "employed at"
+  Property ;      D -> T      -- property of things,     e.g. "employed at Google"
+  Individual ;    D           -- one entity,             e.g. "Google"
+  Name ;          D           -- person, company...      e.g. "Eric Schmidt"
+
+
+Characteristics:
+- simple AST's, lots of variants (easily hundreds per query)
+- semantic overgeneration, e.g. "Google works at Larry Page"
+- some ambiguities, e.g.
+
+    > give me the organizations and their locations
+    MQuery (QFun Location (SAll Organization))
+    MQuery (QFunPair (SAll Organization) Location)
+   
+  Maybe harmless?
+
+Resource grammar was not quite enough; added for instance multiple interrogatives
+("who is employed as what where") in Extra and ExtraEng
+