% % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % %
%                                                                           %
% File:            nation.dtr                                               %
% Purpose:         analysis of nationality adjectives in English            %
% Author:          Geoffrey K. Pullum, October 15, 1994                     %
% Email:           gkp@ling.ucsc.edu                                        %
% Address:         Stevenson College, UCSC, Santa Cruz, CA 95064, USA       %
%                                                                           %
%          Copyright (c) UC Santa Cruz, 1994.  All rights reserved.         %
%                                                                           %
% % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % %

% Phonological representations:
%   ae    cardinal 4+ vowel (ash)
%   ay    cardinal 4-1 diphthong
%   au    cardinal 6 vowel
%   ch    voiceless palato-alveolar affricate
%   j     voiced palato-alveolar affricate
%   &     silent front vowel causing velar softening ([k] --> [s])
%   e     cardinal 2
%   ey    cardinal 3-1 diphthong
%   @r    rhotacized central unrounded vowel
%   ii    long (tense) cardinal 1 vowel
%   ng    voiced velar nasal
%   sh    voiceless palato-alveolar fricative
%   y     voiced palatal central approximant

# vars $v: a aa e ee i ii o oo u uu ae au .

% The Null node defines a message that is shown when a form does not exist:

Null:
    <> == '-- nonexistent --'.

% The Morphonology node is a function doing some crude morphophonemics:

Morphonology:
    <> ==
    <!> ==
    <$seg> == $seg <>
    <l l> == l <>
    <k &> == s <>
    <g i> == j <>
    <n g> == ng g <>
    <o r> == aur <>
    <a u> == a <>
    <$v i @> == $v y @ <>
    <i @> == i y @ <>
    <t i $v> == sh $v <>.

% Nation is the main set of defaults for nation-state-name lexemes.
% A nation-state noun like `Russia' is typically a nationality noun stem plus
% a suffix, typically -a; a nationality noun stem like `Russi-' is typically
% a root plus a stem augment; a nationality adjective like `Russian' is a stem
% plus an adjectival suffix; an inhabitant noun (as in `a Russian') is usually
% like the nationality adjective.  By default, there is no generic plural
% adjective, hence no `*The Russian are coming'.

Nation:
    <mor nat noun form> == "<mor nat noun stem>" "<mor nat noun sufx>"
    <mor nat noun stem> == "<mor nat noun root>" "<mor nat noun augm>"
    <mor nat adjv form> == "<mor nat adjv stem>" "<mor nat adjv sufx>"
    <mor nat adjv stem> == "<mor nat noun stem>"
    <mor inhab noun form> == "<mor nat adjv form>"
    <mor inhab genericpluradjv> == Null
    <mor nat noun augm> ==
    <mor nat noun sufx> == @
    <mor nat adjv sufx> == @ n
    <mor nat noun altform> == Null
    <mor inhab noun xman form> == Null
    <mor inhab noun altform> == Null
    <mor nat adjv altform> == Null
    <phon> == Morphonology:<"<mor>" !>.

% The Land node deals with nationality words typically having nation-state
% noun in -land and nationality adjective in -ish, e.g. England, English,
% and these have a generic plural adjective as in `The English are coming':

Land:
    <> == Nation
    <mor inhab genericpluradjv> == "<mor nat adjv form>"
    <mor inhab noun form> == "<mor nat noun root>"
    <mor nat adjv sufx> == i sh
    <mor nat noun sufx> == l @ n d
    <mor nat noun form> == "<mor nat noun root>" "<mor nat noun sufx>".

% The Ese node deals with nationality words with nationality adjective
% in -ese, e.g. China, Chinese.  These have a generic plural adjective
% as in `The Chinese are coming', but in the author's dialect they lack
% the inhabitant noun form (*a Chinese, *several Chinese) -- though this
% is known from other dialects and can be accounted for through a simple
% modification:

Ese:
    <> == Nation
    <mor nat adjv sufx> == i z
    <mor inhab genericpluradjv> == "<mor nat adjv form>"
    <mor inhab noun form> == Null.

% For those dialects accepting `a Chinese', include the following:
%   <mor inhab noun form> == "<mor nat adjv form>"

% The Stan node is for country lexemes with adjective in -i, e.g. Iraqi:

Stan:
    <> == Nation
    <mor nat adjv sufx> == i
    <mor nat noun sufx> ==.

Islands:
    <> == Nation
    <mor nat noun sufx> == @ z.

% The Xman node is for the properties of the (vaguely archaic or demeaning)
% alternative inhabitant noun forms in -man:

Xman:
    <mor inhab noun xman base> == "<mor nat adjv form>"
    <mor inhab noun xman form> == "<mor inhab noun xman base>" m @ n.

% % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % %

% The countries of the world

Afghanistan:
    <> == Stan
    <sem> == 'Republic of Afghanistan'
    <mor nat noun root> == ae f g ae n i s t aa n.

Albania:
    <> == Nation
    <sem> == 'Republic of Albania'
    <mor nat noun root> == ae l b ey n
    <mor nat noun augm> == i.

Algeria:
    <> == Nation
    <sem> == 'Democratic and Popular Republic of Afghanistan'
    <mor nat noun root> == ae l j ii r
    <mor nat noun augm> == i.

America:
    <> == Nation
    <sem> == 'United States of America'
    <mor nat noun root> == @ m e r i k
    <mor nat noun altform> == 'USA'.

Andorra:
    <> == Nation
    <sem> == 'Principality of Andorra'
    <mor nat noun root> == ae n d o r.

Angola:
    <> == Nation
    <sem> == 'Republic of Angola'
    <mor nat noun root> == ae n g o l.

Antigua:
    <> == Nation
    <sem> == 'Antigua and Barbuda'
    <mor nat noun root> == ae n t ii g w.

Arabia:
    <> == Nation
    <sem> == 'Kingdom of Saudi Arabia'
    <mor nat noun root> == @ r ey b
    <mor nat noun augm> == i.

Argentina:
    <> == Nation
    <sem> == 'Argentine Republic'
    <mor nat noun root> == aa r j @ n t ii n
    <mor inhab noun xman form> == aa r j @ n t ay n
    <mor nat noun augm> == i.

Armenia:
    <> == Nation
    <sem> == 'Republic of Armenia'
    <mor nat noun root> == aa r m ii n
    <mor nat noun augm> == i.

Australia:
    <> == Nation
    <sem> == 'Commonwealth of Australia'
    <mor nat noun root> == a u s t r ey l
    <mor nat noun augm> == i.

Austria:
    <> == Nation
    <sem> == 'Republic of Austria'
    <mor nat noun root> == a u s t r
    <mor nat noun augm> == i.

Azerbaijan:
    <> == Stan
    <sem> == 'Azerbaijani Republic'
    <mor nat noun root> == ae z @r b ay j aa n.

Bahamas:
    <> == Islands
    <sem> == 'The Bahamas'
    <mor nat noun root> == b @ h aa m
    <mor nat adjv stem> == b @ h ey m i.

Bahrain:
    <> == Stan
    <sem> == 'State of Bahrain'
    <mor nat noun root> == b aa r ey n.

Bangladesh:
    <> == Stan
    <sem> == 'Peoples Republic of Bangladesh'
    <mor nat noun root> == b ae n g l @ d ey sh.

Barbados:
    <> == Nation
    <sem> == 'Barbados'
    <mor nat noun root> == b aa r b ey d
    <mor nat noun form> == <mor nat noun root> o s
    <mor nat noun augm> == i.

Barbuda:
    <> == Nation
    <sem> == 'Antigua and Barbuda'
    <mor nat noun root> == b aa r b u d.

Belarus:
    <> == Nation
    <sem> == 'Republic of Belarus'
    <mor nat noun root> == b ey l @ r uu s
    <mor nat noun sufx> ==
    <mor nat adjv stem> == b ey l @ r @ sh.

Belgium:
    <> == Nation
    <sem> == 'Kingdom of Belgium'
    <mor nat noun root> == b e l j
    <mor nat noun sufx> == @ m.

Belize:
    <> == Nation
    <sem> == 'Belize'
    <mor nat noun root> == b e l i z
    <mor nat noun form> == b e l i z
    <mor nat noun augm> == i.

Benin:
    <> == Nation
    <sem> == 'Republic of Benin'
    <mor nat noun root> == b e n i n
    <mor nat noun form> == b e n i n
    <mor nat noun augm> == i.

Bhutan:
    <> == Ese
    <sem> == 'Kingdom of Bhutan'
    <mor nat noun root> == b uu t aa n
    <mor nat adjv stem> == b uu t @ n.

Bolivia:
    <> == Nation
    <sem> == 'Republic of Bolivia'
    <mor nat noun root> == b o l i v
    <mor nat noun augm> == i.

Bosnia:
    <> == Nation
    <sem> == 'Bosnia and Herzegovina'
    <mor nat noun root> == b o z n
    <mor nat noun augm> == i.

Botswana:
    <> == Nation
    <sem> == 'Republic of Botswana'
    <mor nat noun root> == b o t s w aa n.

Brazil:
    <> == Nation
    <sem> == 'Federative Republic of Brazil'
    <mor nat noun root> == b r @ z i l
    <mor nat noun augm> == i.

Britain:
    <> == Land
    <sem> == 'United Kingdom of Great Britain and Northern Ireland'
    <mor nat noun root> == b r i t
    <mor nat noun sufx> == @ n.

Brunei:
    <> == Nation
    <sem> == 'Brunei Darussalam'
    <mor nat noun root> == b r uu n e i.

Bulgaria:
    <> == Nation
    <sem> == 'Republic of Bulgaria'
    <mor nat noun root> == b @ l g e r
    <mor nat noun augm> == i.

%   Burkina Faso:   ?
%       <> == Nation.

Burma:
    <> == Ese
    <sem> == 'Union of Myanmar'
    <mor nat noun root> b @r m.

Burundi:
    <> == Nation
    <sem> == 'Republic of Burundi'
    <mor nat noun augm> == i.

Cambodia:
    <> == Nation
    <sem> == 'State of Cambodia'
    <mor nat noun root> == k ae m b o d
    <mor nat noun augm> == i.

Cameroon:
    <> == Nation
    <sem> == 'Republic of Cameroon'
    <mor nat noun root> == k ae m @r uu n
    <mor nat noun augm> == i.

Canada:
    <> == Nation
    <sem> == 'Canada'
    <mor nat noun root> == k a n a d
    <mor nat noun augm> == i
    <mor nat noun form> == <mor nat noun root> a.

Chad:
    <> == Nation
    <sem> == 'Republic of Chad'
    <mor nat noun root> == ch ae d
    <mor nat noun augm> == i.

Chile:
    <> == Nation
    <sem> == 'Republic of Chile'
    <mor nat noun root> == ch i l e
    <mor nat noun sufx> == .

China:
    <> == Ese
    <sem> == 'Peoples Republic of China'
    <mor nat noun root> == ch ay n
    <mor inhab noun xman base> == <mor nat noun form>
    <mor inhab noun xman form> == Xman.

Colombia:
    <> == Nation
    <sem> == 'Republic of Colombia'
    <mor nat noun root> == k @ l @ m b.

Comoros:
    <> == Nation
    <sem> == 'Federal Islamic Republic of the Comoros'
    <mor nat noun root> == k o m @ r o.

Congo:
    <> == Ese
    <sem> == 'Republic of Congo'
    <mor nat noun form> == <mor nat noun root>
    <mor nat noun root> == k a n g o
    <mor nat noun augm> == l.

CostaRica:
    <> == Nation
    <sem> == 'Republic of Costa Rica'
    <mor nat noun root> == k o s t a r ii k.

Croatia:
    <> == Nation
    <sem> == 'Republic of Croatia'
    <mor nat noun root> == k r o ey t
    <mor nat noun augm> == i.

Cuba:
    <> == Nation
    <sem> == 'Republic of Cuba'
    <mor nat noun root> == k y uu b.

Cyprus:
    <> == Nation
    <sem> == 'Republic of Cyprus'
    <mor nat noun root> == s ay p r
    <mor nat noun sufx> == @ s
    <mor nat adjv stem> == s i p r i
    <mor nat adjv sufx> == @ t.

Czechoslovakia:
    <> == Nation
    <sem> == 'Czech and Slovak Federal Republic'
    <mor nat noun root> == ch e k o s l o v ae k
    <mor inhab noun form> == Null
    <mor nat noun augm> == i.

Denmark:
    <> == Land
    <sem> == 'Kingdom of Denmark'
    <mor nat noun form> == d e n m a r k
    <mor nat noun root> == d ey n.

Djibouti:
    <> == Nation
    <sem> == 'Republic of Djibouti'
    <mor nat noun root> == j i b uu t
    <mor nat noun augm> == i
    <mor nat noun sufx> ==.

Dominica:
    <> == Nation
    <sem> == 'Commonwealth of Dominica'
    <mor nat noun root> == d a m i n ii k.

Ecuador:
    <> == Nation
    <sem> == 'Republic of Ecuador'
    <mor nat noun root> == e k w @ d o r
    <mor nat noun augm> == i.

Egypt:
    <> == Nation
    <sem> == 'Arab Republic of Egypt'
    <mor nat noun root> == ii j i p t
    <mor nat noun augm> == i.

ElSalvador:
    <> == Nation
    <sem> == 'Republic of El Salvador'
    <mor nat noun root> == s ae l v @ d o r
    <mor nat noun augm> == i.

Eritrea:
    <> == Nation
    <sem> == 'State of Eritrea'
    <mor nat noun root> == e r i t r ey.

Estonia:
    <> == Nation
    <sem> == 'Republic of Estonia'
    <mor nat noun root> == e s t o n
    <mor nat noun augm> == i.

England:
    <> == Land
    <sem> == 'England'
    <mor nat noun root> == i n g l
    <mor inhab noun form> == Null
    <mor inhab noun xman> == Xman.

Ethiopia:
    <> == Nation
    <sem> == 'Ethiopia'
    <mor nat noun root> == ii th i o p
    <mor nat noun augm> == i.

Fiji:
    <> == Nation
    <sem> == 'Republic of Fiji'
    <mor nat noun root> == f i j i.

Finland:
    <> == Land
    <sem> == 'Republic of Finland'
    <mor nat noun root> == f i n.

France:
    <> == Nation
    <sem> == 'French Republic'
    <mor nat noun root> == f r ae n k
    <mor nat adjv form> == f r e n ch
    <mor inhab noun form> == Null
    <mor inhab noun xman> == Xman
    <mor nat noun sufx> == &.

Gabon:
    <> == Ese
    <sem> == 'Gabonese Republic'
    <mor nat noun root> == g ae b a n.

Gambia:
    <> == Nation
    <sem> == 'Republic of the Gambia'
    <mor nat noun root> == g ae m b
    <mor nat noun augm> == i.

Georgia:
    <> == Nation
    <sem> == 'Republic of Georgia'
    <mor nat noun root> == j o r j.

Germany:
    <> == Nation
    <sem> == 'Federal Republic of Germany'
    <mor nat noun root> == j @r m
    <mor nat noun form> == <mor nat adjv form> y.

Ghana:
    <> == Nation
    <sem> == 'Republic of Ghana'
    <mor nat noun root> == g aa n
    <mor nat adjv stem> == g aa n ey.

Greece:
    <> == Nation
    <sem> == 'Hellenic Republic'
    <mor nat noun root> == g r ii k
    <mor nat noun sufx> == &.

Greenland:
    <> == Land
    <sem> == 'Kalaallit Nunaat'
    <mor nat noun root> == g r ii n
    <mor nat adjv form> == <mor nat noun root> l ae n d i k
    <mor inhab noun form> == <mor nat noun form> @r.

Grenada:
    <> == Nation
    <sem> == 'Grenada'
    <mor nat noun root> == g r e n ey d
    <mor nat noun augm> == i.

Guatemala:
    <> == Nation
    <sem> == 'Republic of Guatemala'
    <mor nat noun root> == g w a t @ m aa l.

Guinea:
    <> == Nation
    <sem> == 'Republic of Guinea'
    <mor nat noun root> == g i n i
    <mor nat noun sufx> == .

Guyana:
    <> == Nation
    <sem> == 'Co-operative Republic of Guyana'
    <mor nat noun root> == g ay aa n.

Haiti:
    <> == Nation
    <sem> == 'Republic of Haiti'
    <mor nat noun root> == h ey t i.

Holland:
    <> == Land
    <mor nat noun root> == h a l
    <mor nat noun altform> == n e dh @r l @ n d z
    <mor nat adjv form> == d @ ch
    <mor inhab noun xman> == Xman
    <mor inhab noun form> == Null.

Hungary:
    <> == Nation
    <mor nat noun root> == h @ n g e r
    <mor nat noun augm> == i.

Iceland:
    <> == Land
    <mor nat noun root> == ay s
    <mor nat adjv form> == <mor nat noun root> l ae n d i k
    <mor inhab noun form> == <mor nat noun form> @r.

India:
    <> == Nation
    <mor nat noun root> == i n d
    <mor nat noun augm> == i.

Ireland:
    <> == Land
    <mor nat noun root> == ay r
    <mor nat noun altform> == e@r @
    <mor inhab noun xman> == Xman.

Iraq:
    <> == Stan
    <mor nat noun root> == i r ae k.

Israel:
    <> == Stan
    <mor nat noun root> == i z r ey l.

Italy:
    <> == Nation
    <mor nat noun root> == i t ae l
    <mor nat noun augm> == i
    <mor nat noun form> == <mor nat noun root> y.

Liechtenstein:
    <> == Nation
    <mor nat noun root> == l i k t @ n s t ay n
    <mor nat noun form> == <mor nat noun root>
    <mor nat noun augm> == i.

Luxembourg:
    <> == Nation
    <mor nat noun root> == l @ k s @ m b @r g
    <mor nat noun augm> == i
    <mor nat noun form> == <mor nat noun root>.

Mexico:
    <> == Nation
    <mor nat noun root> == m e k s i k
    <mor nat noun sufx> == o.

Nauru:
    <> == Nation
    <mor nat noun root> == n a u r u.

Norway:
    <> == Nation
    <mor nat noun root> == n o r w
    <mor nat noun sufx> == ey
    <mor nat noun form> == <mor nat noun root> <mor nat noun sufx>
    <mor nat noun augm> == ii j.

Pakistan:
    <> == Stan
    <mor nat noun root> == p aa k i s t aa n.

Poland:
    <> == Land
    <mor nat noun root> == p o l
    <mor inhab noun form> == <mor nat noun stem>.

Portugal:
    <> == Ese
    <mor nat noun root> == p o r t j u g
    <mor nat adjv sufx> == i z
    <mor nat noun sufx> == @ l.

Scotland:
    <> == Land
    <mor nat noun root> == s k a t
    <mor nat adjv altform> == <mor nat noun root> s
    <mor inhab noun xman base> == <mor nat adjv altform>.

Slovakia:
    <> == Nation
    <mor nat noun root> == s l o v ae k
    <mor inhab noun form> == <mor nat noun root>
    <mor nat noun augm> == i.

Spain:
    <> == Nation
    <mor nat noun root> == s p ae n
    <mor nat noun form> == s p ey n
    <mor nat adjv sufx> == Land
    <mor inhab noun form> == <mor nat noun root> y a r d.

Sweden:
    <> == Nation
    <mor nat noun root> == s w ii d
    <mor nat noun sufx> == en
    <mor nat adjv sufx> == Land.

Switzerland:
    <> == Land
    <mor nat adjv sufx> == s
    <mor nat noun root> == s w i
    <mor nat noun augm> == t s @r
    <mor inhab noun form> == Null.

Turkey:
    <> == Land
    <mor nat noun root> == t @r k
    <mor nat noun sufx> == i.

Wales:
    <> == Land
    <mor nat noun form> == w ey l z
    <mor nat adjv form> == w e l sh
    <mor inhab noun form> == Null
    <mor inhab noun xman> == Xman.

% % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % %

% Some example theorems:
%
% Wales:
%   <mor nat noun form> = w ey l z
%   <phon nat noun form> = w ey l z
%   <mor inhab noun form> = -- nonexistent --
%   <phon inhab noun form> = -- nonexistent --
%   <mor inhab noun xman form> = w e l sh m @ n
%   <phon inhab noun xman form> = w e l sh m @ n
%   <mor nat adjv form> = w e l sh
%   <phon nat adjv form> = w e l sh
%   <mor inhab genericpluradjv> = w e l sh
%   <phon inhab genericpluradjv> = w e l sh
%   <mor nat adjv altform> = -- nonexistent --
%   <phon nat adjv altform> = -- nonexistent --.

% % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % %

# hide Ese Land Morphonology Nation Null Stan Xman Islands.

# show
    <mor nat noun form>
    <phon nat noun form>
    <mor inhab noun form>
    <phon inhab noun form>
    <mor inhab noun xman form>
    <phon inhab noun xman form>
    <mor nat adjv form>
    <phon nat adjv form>
    <mor inhab genericpluradjv>
    <phon inhab genericpluradjv>
    <mor nat adjv altform>
    <phon nat adjv altform>.

% % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % %

% The next line is the Revision Control System Archive Id: do not delete it.
% $Id: archive.dtr,v 1.1 1997/04/09 20:40:33 root Exp $