mirror of
https://github.com/GrammaticalFramework/gf-core.git
synced 2026-04-12 06:19:33 -06:00
596 lines
14 KiB
HTML
596 lines
14 KiB
HTML
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
|
|
<HTML>
|
|
<HEAD>
|
|
<META NAME="generator" CONTENT="http://txt2tags.sf.net">
|
|
</HEAD><BODY BGCOLOR="white" TEXT="black">
|
|
<FONT SIZE="4">
|
|
</FONT></CENTER>
|
|
|
|
<P></P>
|
|
<HR NOSHADE SIZE=1>
|
|
<P></P>
|
|
<P></P>
|
|
<HR NOSHADE SIZE=1>
|
|
<P></P>
|
|
<P>
|
|
Author:
|
|
Last update: Tue Jan 17 15:24:36 2006
|
|
</P>
|
|
<P>
|
|
Produced by
|
|
gfdoc - a rudimentary GF document generator.
|
|
(c) Aarne Ranta (<A HREF="mailto:aarne@cs.chalmers.se">aarne@cs.chalmers.se</A>) 2002 under GNU GPL.
|
|
</P>
|
|
<P>
|
|
==
|
|
</P>
|
|
<P>
|
|
--# -path=.:../abstract:../../prelude
|
|
</P>
|
|
<P>
|
|
--1 Dutlish Lexical Paradigms
|
|
--
|
|
-- Aarne Ranta 2003--2005
|
|
--
|
|
-- This is an API to the user of the resource grammar
|
|
-- for adding lexical items. It gives functions for forming
|
|
-- expressions of open categories: nouns, adjectives, verbs.
|
|
--
|
|
-- Closed categories (determiners, pronouns, conjunctions) are
|
|
-- accessed through the resource syntax API, <CODE>Structural.gf</CODE>.
|
|
--
|
|
-- The main difference with <CODE>MorphoDut.gf</CODE> is that the types
|
|
-- referred to are compiled resource grammar types. We have moreover
|
|
-- had the design principle of always having existing forms, rather
|
|
-- than stems, as string arguments of the paradigms.
|
|
--
|
|
-- The structure of functions for each word class <CODE>C</CODE> is the following:
|
|
-- first we give a handful of patterns that aim to cover all
|
|
-- regular cases. Then we give a worst-case function <CODE>mkC</CODE>, which serves as an
|
|
-- escape to construct the most irregular words of type <CODE>C</CODE>.
|
|
-- However, this function should only seldom be needed: we have a
|
|
-- separate module <CODE>IrregularDut</CODE>, which covers all irregularly inflected
|
|
-- words.
|
|
--
|
|
-- The following modules are presupposed:
|
|
</P>
|
|
<P>
|
|
resource ParadigmsDut = open
|
|
(Predef=Predef),
|
|
Prelude,
|
|
MorphoDut,
|
|
CatDut
|
|
in {
|
|
--2 Parameters
|
|
--
|
|
-- To abstract over gender names, we define the following identifiers.
|
|
</P>
|
|
<P>
|
|
oper
|
|
Gender : Type ;
|
|
</P>
|
|
<P>
|
|
human : Gender ;
|
|
nonhuman : Gender ;
|
|
masculine : Gender ;
|
|
feminite : Gender ;
|
|
</P>
|
|
<P>
|
|
-- To abstract over number names, we define the following.
|
|
</P>
|
|
<P>
|
|
Number : Type ;
|
|
</P>
|
|
<P>
|
|
singular : Number ;
|
|
plural : Number ;
|
|
</P>
|
|
<P>
|
|
-- To abstract over case names, we define the following.
|
|
</P>
|
|
<P>
|
|
Case : Type ;
|
|
</P>
|
|
<P>
|
|
nominative : Case ;
|
|
genitive : Case ;
|
|
</P>
|
|
<P>
|
|
-- Prepositions are used in many-argument functions for rection.
|
|
</P>
|
|
<P>
|
|
Preposition : Type ;
|
|
</P>
|
|
<P>
|
|
--2 Nouns
|
|
</P>
|
|
<P>
|
|
-- Worst case: give all four forms and the semantic gender.
|
|
</P>
|
|
<P>
|
|
mkN : (man,men,man's,men's : Str) -> N ;
|
|
</P>
|
|
<P>
|
|
-- The regular function captures the variants for nouns ending with
|
|
-- <I>s</I>,<I>sh</I>,<I>x</I>,<I>z</I> or <I>y</I>: <I>kiss - kisses</I>, <I>flash - flashes</I>;
|
|
-- <I>fly - flies</I> (but <I>toy - toys</I>),
|
|
</P>
|
|
<P>
|
|
regN : Str -> N ;
|
|
</P>
|
|
<P>
|
|
-- In practice the worst case is just: give singular and plural nominative.
|
|
</P>
|
|
<P>
|
|
mk2N : (man,men : Str) -> N ;
|
|
</P>
|
|
<P>
|
|
-- All nouns created by the previous functions are marked as
|
|
-- <CODE>nonhuman</CODE>. If you want a <CODE>human</CODE> noun, wrap it with the following
|
|
-- function:
|
|
</P>
|
|
<P>
|
|
genderN : Gender -> N -> N ;
|
|
</P>
|
|
<P>
|
|
--3 Compound nouns
|
|
--
|
|
-- All the functions above work quite as well to form compound nouns,
|
|
-- such as <I>baby boom</I>.
|
|
</P>
|
|
<P>
|
|
--3 Relational nouns
|
|
--
|
|
-- Relational nouns (<I>daughter of x</I>) need a preposition.
|
|
</P>
|
|
<P>
|
|
mkN2 : N -> Preposition -> N2 ;
|
|
</P>
|
|
<P>
|
|
-- The most common preposition is <I>of</I>, and the following is a
|
|
-- shortcut for regular, <CODE>nonhuman</CODE> relational nouns with <I>of</I>.
|
|
</P>
|
|
<P>
|
|
regN2 : Str -> N2 ;
|
|
</P>
|
|
<P>
|
|
-- Use the function <CODE>mkPreposition</CODE> or see the section on prepositions below to
|
|
-- form other prepositions.
|
|
--
|
|
-- Three-place relational nouns (<I>the connection from x to y</I>) need two prepositions.
|
|
</P>
|
|
<P>
|
|
mkN3 : N -> Preposition -> Preposition -> N3 ;
|
|
</P>
|
|
<P>
|
|
--3 Relational common noun phrases
|
|
--
|
|
-- In some cases, you may want to make a complex <CODE>CN</CODE> into a
|
|
-- relational noun (e.g. <I>the old town hall of</I>).
|
|
</P>
|
|
<P>
|
|
cnN2 : CN -> Preposition -> N2 ;
|
|
cnN3 : CN -> Preposition -> Preposition -> N3 ;
|
|
</P>
|
|
<P>
|
|
--
|
|
--3 Proper names and noun phrases
|
|
--
|
|
-- Proper names, with a regular genitive, are formed as follows
|
|
</P>
|
|
<P>
|
|
regPN : Str -> Gender -> PN ; -- John, John's
|
|
</P>
|
|
<P>
|
|
-- Sometimes you can reuse a common noun as a proper name, e.g. <I>Bank</I>.
|
|
</P>
|
|
<P>
|
|
nounPN : N -> PN ;
|
|
</P>
|
|
<P>
|
|
-- To form a noun phrase that can also be plural and have an irregular
|
|
-- genitive, you can use the worst-case function.
|
|
</P>
|
|
<P>
|
|
mkNP : Str -> Str -> Number -> Gender -> NP ;
|
|
</P>
|
|
<P>
|
|
--2 Adjectives
|
|
</P>
|
|
<P>
|
|
-- Non-comparison one-place adjectives need two forms: one for
|
|
-- the adjectival and one for the adverbial form (<I>free - freely</I>)
|
|
</P>
|
|
<P>
|
|
mkA : (free,freely : Str) -> A ;
|
|
</P>
|
|
<P>
|
|
-- For regular adjectives, the adverbial form is derived. This holds
|
|
-- even for cases with the variation <I>happy - happily</I>.
|
|
</P>
|
|
<P>
|
|
regA : Str -> A ;
|
|
</P>
|
|
<P>
|
|
--3 Two-place adjectives
|
|
--
|
|
-- Two-place adjectives need a preposition for their second argument.
|
|
</P>
|
|
<P>
|
|
mkA2 : A -> Preposition -> A2 ;
|
|
</P>
|
|
<P>
|
|
-- Comparison adjectives may two more forms.
|
|
</P>
|
|
<P>
|
|
ADeg : Type ;
|
|
</P>
|
|
<P>
|
|
mkADeg : (good,better,best,well : Str) -> ADeg ;
|
|
</P>
|
|
<P>
|
|
-- The regular pattern recognizes two common variations:
|
|
-- <I>-e</I> (<I>rude</I> - <I>ruder</I> - <I>rudest</I>) and
|
|
-- <I>-y</I> (<I>happy - happier - happiest - happily</I>)
|
|
</P>
|
|
<P>
|
|
regADeg : Str -> ADeg ; -- long, longer, longest
|
|
</P>
|
|
<P>
|
|
-- However, the duplication of the final consonant is nor predicted,
|
|
-- but a separate pattern is used:
|
|
</P>
|
|
<P>
|
|
duplADeg : Str -> ADeg ; -- fat, fatter, fattest
|
|
</P>
|
|
<P>
|
|
-- If comparison is formed by <I>more, //most</I>, as in general for//
|
|
-- long adjective, the following pattern is used:
|
|
</P>
|
|
<P>
|
|
compoundADeg : A -> ADeg ; -- -/more/most ridiculous
|
|
</P>
|
|
<P>
|
|
-- From a given <CODE>ADeg</CODE>, it is possible to get back to <CODE>A</CODE>.
|
|
</P>
|
|
<P>
|
|
adegA : ADeg -> A ;
|
|
</P>
|
|
<P>
|
|
--2 Adverbs
|
|
</P>
|
|
<P>
|
|
-- Adverbs are not inflected. Most lexical ones have position
|
|
-- after the verb. Some can be preverbal (e.g. <I>always</I>).
|
|
</P>
|
|
<P>
|
|
mkAdv : Str -> Adv ;
|
|
mkAdV : Str -> AdV ;
|
|
</P>
|
|
<P>
|
|
-- Adverbs modifying adjectives and sentences can also be formed.
|
|
</P>
|
|
<P>
|
|
mkAdA : Str -> AdA ;
|
|
</P>
|
|
<P>
|
|
--2 Prepositions
|
|
--
|
|
-- A preposition as used for rection in the lexicon, as well as to
|
|
-- build <CODE>PP</CODE>s in the resource API, just requires a string.
|
|
</P>
|
|
<P>
|
|
mkPreposition : Str -> Preposition ;
|
|
mkPrep : Str -> Prep ;
|
|
</P>
|
|
<P>
|
|
-- (These two functions are synonyms.)
|
|
</P>
|
|
<P>
|
|
--2 Verbs
|
|
--
|
|
-- Except for <I>be</I>, the worst case needs five forms: the infinitive and
|
|
-- the third person singular present, the past indicative, and the
|
|
-- past and present participles.
|
|
</P>
|
|
<P>
|
|
mkV : (go, goes, went, gone, going : Str) -> V ;
|
|
</P>
|
|
<P>
|
|
-- The regular verb function recognizes the special cases where the last
|
|
-- character is <I>y</I> (<I>cry - cries</I> but <I>buy - buys</I>) or <I>s</I>, <I>sh</I>, <I>x</I>, <I>z</I>
|
|
-- (<I>fix - fixes</I>, etc).
|
|
</P>
|
|
<P>
|
|
regV : Str -> V ;
|
|
</P>
|
|
<P>
|
|
-- The following variant duplicates the last letter in the forms like
|
|
-- <I>rip - ripped - ripping</I>.
|
|
</P>
|
|
<P>
|
|
regDuplV : Str -> V ;
|
|
</P>
|
|
<P>
|
|
-- There is an extensive list of irregular verbs in the module <CODE>IrregularDut</CODE>.
|
|
-- In practice, it is enough to give three forms,
|
|
-- e.g. <I>drink - drank - drunk</I>, with a variant indicating consonant
|
|
-- duplication in the present participle.
|
|
</P>
|
|
<P>
|
|
irregV : (drink, drank, drunk : Str) -> V ;
|
|
irregDuplV : (get, got, gotten : Str) -> V ;
|
|
</P>
|
|
<P>
|
|
--3 Verbs with a particle.
|
|
--
|
|
-- The particle, such as in <I>switch on</I>, is given as a string.
|
|
</P>
|
|
<P>
|
|
partV : V -> Str -> V ;
|
|
</P>
|
|
<P>
|
|
--3 Two-place verbs
|
|
--
|
|
-- Two-place verbs need a preposition, except the special case with direct object.
|
|
-- (transitive verbs). Notice that a particle comes from the <CODE>V</CODE>.
|
|
</P>
|
|
<P>
|
|
mkV2 : V -> Preposition -> V2 ;
|
|
</P>
|
|
<P>
|
|
dirV2 : V -> V2 ;
|
|
</P>
|
|
<P>
|
|
--3 Three-place verbs
|
|
--
|
|
-- Three-place (ditransitive) verbs need two prepositions, of which
|
|
-- the first one or both can be absent.
|
|
</P>
|
|
<P>
|
|
mkV3 : V -> Str -> Str -> V3 ; -- speak, with, about
|
|
dirV3 : V -> Str -> V3 ; -- give,_,to
|
|
dirdirV3 : V -> V3 ; -- give,_,_
|
|
</P>
|
|
<P>
|
|
--3 Other complement patterns
|
|
--
|
|
-- Verbs and adjectives can take complements such as sentences,
|
|
-- questions, verb phrases, and adjectives.
|
|
</P>
|
|
<P>
|
|
mkV0 : V -> V0 ;
|
|
mkVS : V -> VS ;
|
|
mkV2S : V -> Str -> V2S ;
|
|
mkVV : V -> VV ;
|
|
mkV2V : V -> Str -> Str -> V2V ;
|
|
mkVA : V -> VA ;
|
|
mkV2A : V -> Str -> V2A ;
|
|
mkVQ : V -> VQ ;
|
|
mkV2Q : V -> Str -> V2Q ;
|
|
</P>
|
|
<P>
|
|
mkAS : A -> AS ;
|
|
mkA2S : A -> Str -> A2S ;
|
|
mkAV : A -> AV ;
|
|
mkA2V : A -> Str -> A2V ;
|
|
</P>
|
|
<P>
|
|
-- Notice: categories <CODE>V2S, V2V, V2A, V2Q</CODE> are in v 1.0 treated
|
|
-- just as synonyms of <CODE>V2</CODE>, and the second argument is given
|
|
-- as an adverb. Likewise <CODE>AS, A2S, AV, A2V</CODE> are just <CODE>A</CODE>.
|
|
-- <CODE>V0</CODE> is just <CODE>V</CODE>.
|
|
</P>
|
|
<P>
|
|
V0, V2S, V2V, V2A, V2Q : Type ;
|
|
AS, A2S, AV, A2V : Type ;
|
|
</P>
|
|
<P>
|
|
--2 Definitions of paradigms
|
|
--
|
|
-- The definitions should not bother the user of the API. So they are
|
|
-- hidden from the document.
|
|
--.
|
|
</P>
|
|
<P>
|
|
Gender = MorphoDut.Gender ;
|
|
Number = MorphoDut.Number ;
|
|
Case = MorphoDut.Case ;
|
|
human = Masc ;
|
|
nonhuman = Neutr ;
|
|
masculine = Masc ;
|
|
feminine = Fem ;
|
|
singular = Sg ;
|
|
plural = Pl ;
|
|
nominative = Nom ;
|
|
genitive = Gen ;
|
|
</P>
|
|
<P>
|
|
Preposition = Str ;
|
|
</P>
|
|
<P>
|
|
regN = \ray ->
|
|
let
|
|
ra = Predef.tk 1 ray ;
|
|
y = Predef.dp 1 ray ;
|
|
r = Predef.tk 2 ray ;
|
|
ay = Predef.dp 2 ray ;
|
|
rays =
|
|
case y of {
|
|
<I>y</I> => y2ie ray <I>s</I> ;
|
|
<I>s</I> => ray + <I>es</I> ;
|
|
<I>z</I> => ray + <I>es</I> ;
|
|
<I>x</I> => ray + <I>es</I> ;
|
|
_ => case ay of {
|
|
<I>sh</I> => ray + <I>es</I> ;
|
|
<I>ch</I> => ray + <I>es</I> ;
|
|
_ => ray + <I>s</I>
|
|
}
|
|
}
|
|
in
|
|
mk2N ray rays ;
|
|
</P>
|
|
<P>
|
|
mk2N = \man,men ->
|
|
let mens = case last men of {
|
|
<I>s</I> => men + <I>'</I> ;
|
|
_ => men + <I>'s</I>
|
|
}
|
|
in
|
|
mkN man men (man + <I>'s</I>) mens ;
|
|
</P>
|
|
<P>
|
|
mkN = \man,men,man's,men's ->
|
|
mkNoun man men man's men's **** {g = Neutr ; lock_N = <>} ;
|
|
</P>
|
|
<P>
|
|
genderN g man = {s = man.s ; g = g ; lock_N = <>} ;
|
|
</P>
|
|
<P>
|
|
mkN2 = \n,p -> n **** {lock_N2 = <> ; c2 = p} ;
|
|
regN2 n = mkN2 (regN n) (mkPreposition <I>of</I>) ;
|
|
mkN3 = \n,p,q -> n **** {lock_N3 = <> ; c2 = p ; c3 = q} ;
|
|
cnN2 = \n,p -> n **** {lock_N2 = <> ; c2 = p} ;
|
|
cnN3 = \n,p,q -> n **** {lock_N3 = <> ; c2 = p ; c3 = q} ;
|
|
</P>
|
|
<P>
|
|
regPN n g = nameReg n g **** {lock_PN = <>} ;
|
|
nounPN n = {s = n.s ! singular ; g = n.g ; lock_PN = <>} ;
|
|
mkNP x y n g = {s = table {Gen => x ; _ => y} ; a = (agrP3 n).a ;
|
|
lock_NP = <>} ;
|
|
</P>
|
|
<P>
|
|
mkA a b = mkAdjective a a a b **** {lock_A = <>} ;
|
|
regA a = regAdjective a **** {lock_A = <>} ;
|
|
</P>
|
|
<P>
|
|
mkA2 a p = a **** {c2 = p ; lock_A2 = <>} ;
|
|
</P>
|
|
<P>
|
|
ADeg = A ; ----
|
|
</P>
|
|
<P>
|
|
mkADeg a b c d = mkAdjective a b c d **** {lock_A = <>} ;
|
|
</P>
|
|
<P>
|
|
regADeg happy =
|
|
let
|
|
happ = init happy ;
|
|
y = last happy ;
|
|
happie = case y of {
|
|
<I>y</I> => happ + <I>ie</I> ;
|
|
<I>e</I> => happy ;
|
|
_ => happy + <I>e</I>
|
|
} ;
|
|
happily = case y of {
|
|
<I>y</I> => happ + <I>ily</I> ;
|
|
_ => happy + <I>ly</I>
|
|
} ;
|
|
in mkADeg happy (happie + <I>r</I>) (happie + <I>st</I>) happily ;
|
|
</P>
|
|
<P>
|
|
duplADeg fat =
|
|
mkADeg fat
|
|
(fat + last fat + <I>er</I>) (fat + last fat + <I>est</I>) (fat + <I>ly</I>) ;
|
|
</P>
|
|
<P>
|
|
compoundADeg a =
|
|
let ad = (a.s ! AAdj Posit)
|
|
in mkADeg ad (<I>more</I> ++ ad) (<I>most</I> ++ ad) (a.s ! AAdv) ;
|
|
</P>
|
|
<P>
|
|
adegA a = a ;
|
|
</P>
|
|
<P>
|
|
mkAdv x = ss x **** {lock_Adv = <>} ;
|
|
mkAdV x = ss x **** {lock_AdV = <>} ;
|
|
mkAdA x = ss x **** {lock_AdA = <>} ;
|
|
</P>
|
|
<P>
|
|
mkPreposition p = p ;
|
|
mkPrep p = ss p **** {lock_Prep = <>} ;
|
|
</P>
|
|
<P>
|
|
mkV a b c d e = mkVerbWorst a b c d e **** {s1 = [] ; lock_V = <>} ;
|
|
</P>
|
|
<P>
|
|
regV cry =
|
|
let
|
|
cr = init cry ;
|
|
y = last cry ;
|
|
cries = (regN cry).s ! Pl ! Nom ; -- !
|
|
crie = init cries ;
|
|
cried = case last crie of {
|
|
<I>e</I> => crie + <I>d</I> ;
|
|
_ => crie + <I>ed</I>
|
|
} ;
|
|
crying = case y of {
|
|
<I>e</I> => case last cr of {
|
|
<I>e</I> => cry + <I>ing</I> ;
|
|
_ => cr + <I>ing</I>
|
|
} ;
|
|
_ => cry + <I>ing</I>
|
|
}
|
|
in mkV cry cries cried cried crying ;
|
|
</P>
|
|
<P>
|
|
regDuplV fit =
|
|
let fitt = fit + last fit in
|
|
mkV fit (fit + <I>s</I>) (fitt + <I>ed</I>) (fitt + <I>ed</I>) (fitt + <I>ing</I>) ;
|
|
</P>
|
|
<P>
|
|
irregV x y z = let reg = (regV x).s in
|
|
mkV x (reg ! VPres) y z (reg ! VPresPart) **** {s1 = [] ; lock_V = <>} ;
|
|
</P>
|
|
<P>
|
|
irregDuplV fit y z =
|
|
let
|
|
fitting = (regDuplV fit).s ! VPresPart
|
|
in
|
|
mkV fit (fit + <I>s</I>) y z fitting ;
|
|
</P>
|
|
<P>
|
|
partV v p = verbPart v p **** {lock_V = <>} ;
|
|
</P>
|
|
<P>
|
|
mkV2 v p = v **** {s = v.s ; s1 = v.s1 ; c2 = p ; lock_V2 = <>} ;
|
|
dirV2 v = mkV2 v [] ;
|
|
</P>
|
|
<P>
|
|
mkV3 v p q = v **** {s = v.s ; s1 = v.s1 ; c2 = p ; c3 = q ; lock_V3 = <>} ;
|
|
dirV3 v p = mkV3 v [] p ;
|
|
dirdirV3 v = dirV3 v [] ;
|
|
</P>
|
|
<P>
|
|
mkVS v = v **** {lock_VS = <>} ;
|
|
mkVV v = v **** {c2 = <I>to</I> ; lock_VV = <>} ;
|
|
mkVQ v = v **** {lock_VQ = <>} ;
|
|
</P>
|
|
<P>
|
|
V0 : Type = V ;
|
|
V2S, V2V, V2Q, V2A : Type = V2 ;
|
|
AS, A2S, AV : Type = A ;
|
|
A2V : Type = A2 ;
|
|
</P>
|
|
<P>
|
|
mkV0 v = v **** {lock_V = <>} ;
|
|
mkV2S v p = mkV2 v p **** {lock_V2 = <>} ;
|
|
mkV2V v p t = mkV2 v p **** {s4 = t ; lock_V2 = <>} ;
|
|
mkVA v = v **** {lock_VA = <>} ;
|
|
mkV2A v p = mkV2 v p **** {lock_V2A = <>} ;
|
|
mkV2Q v p = mkV2 v p **** {lock_V2 = <>} ;
|
|
</P>
|
|
<P>
|
|
mkAS v = v **** {lock_A = <>} ;
|
|
mkA2S v p = mkA2 v p **** {lock_A = <>} ;
|
|
mkAV v = v **** {lock_A = <>} ;
|
|
mkA2V v p = mkA2 v p **** {lock_A2 = <>} ;
|
|
</P>
|
|
<P>
|
|
} ;
|
|
</P>
|
|
|
|
<!-- html code generated by txt2tags 2.0 (http://txt2tags.sf.net) -->
|
|
<!-- cmdline: txt2tags -thtml -\-toc dutch/ParadigmsDut.txt -->
|
|
</BODY></HTML>
|