Skip to content

Commit cf9d341

Browse files
committed
Split off _er and _est from double letter words
1 parent 36952b5 commit cf9d341

File tree

2 files changed

+69374
-69277
lines changed

2 files changed

+69374
-69277
lines changed

src/edu/stanford/nlp/process/Morpha.flex

Lines changed: 5 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -466,6 +466,9 @@ SKIP = [ \t\r\n\u2028\u2029\u000B\u000C\u0085]
466466
/* adjectives such as tame which become tamer, tamest */
467467
E_ADJS = "able"|"absolute"|"abstruse"|"acute"|"ample"|"austere"|"bare"|"base"|"blithe"|"blonde"|"blue"|"brave"|"brittle"|"brusque"|"capable"|"chaste"|"choice"|"close"|"coarse"|"complete"|"concise"|"crude"|"cute"|"demure"|"dense"|"dire"|"divine"|"doggone"|"eerie"|"extreme"|"false"|"feeble"|"fickle"|"fierce"|"fine"|"free"|"game"|"gauche"|"gentle"|"gladsome"|"grave"|"grewsome"|"gruesome"|"hale"|"handsome"|"hoarse"|"huge"|"humane"|"humble"|"idle"|"immense"|"inane"|"insane"|"intense"|"irate"|"kittle"|"lame"|"large"|"late"|"lithe"|"little"|"loose"|"mature"|"mere"|"mickle"|"minute"|"mute"|"naive"|"naïve"|"negative"|"nice"|"nimble"|"noble"|"nude"|"obscene"|"obscure"|"obtuse"|"opaque"|"pale"|"polite"|"positive"|"possible"|"precise"|"private"|"pure"|"purple"|"rare"|"rathe"|"remote"|"resolute"|"rife"|"ripe"|"rude"|"safe"|"sage"|"sane"|"savage"|"scarce"|"secure"|"sensible"|"serene"|"severe"|"simple"|"sincere"|"sore"|"spare"|"sparse"|"spruce"|"square"|"stable"|"stale"|"strange"|"suave"|"sublime"|"subtile"|"subtle"|"supple"|"supreme"|"sure"|"svelte"|"tame"|"tense"|"terse"|"trite"|"true"|"unique"|"unripe"|"unsafe"|"unstable"|"untrue"|"unwise"|"urbane"|"vague"|"vile"|"white"|"wholesome"|"wide"|"winsome"|"wise"|"yare"
468468

469+
/* adjectives such as hot which become hotter, hottest */
470+
XX_ADJS = "awfull"|"badd"|"bigg"|"bumm"|"carefull"|"cheerfull"|"cruell"|"dimm"|"dolefull"|"drabb"|"dunn"|"fatt"|"fearfull"|"fitt"|"flatt"|"flipp"|"fruitfull"|"full"|"gladd"|"glibb"|"glumm"|"gracefull"|"gratefull"|"grimm"|"grumm"|"hipp"|"hott"|"joyfull"|"levell"|"madd"|"mournfull"|"painfull"|"peacefull"|"pitifull"|"primm"|"redd"|"rumm"|"sadd"|"slimm"|"smugg"|"snugg"|"squatt"|"tann"|"thankfull"|"thinn"|"tranquill"|"trimm"|"wann"|"wett"|"woefull"|"wonderfull"
471+
469472

470473
%%
471474

@@ -2092,6 +2095,8 @@ E_ADJS = "able"|"absolute"|"abstruse"|"acute"|"ample"|"austere"|"bare"|"base"|"b
20922095

20932096
<scan>{E_ADJS}r/_JJ { return(stem(1, "", "")); }
20942097
<scan>{E_ADJS}st/_JJ { return(stem(2, "", "")); }
2098+
<scan>{XX_ADJS}er/_JJ { return(stem(3, "", "")); }
2099+
<scan>{XX_ADJS}est/_JJ { return(stem(4, "", "")); }
20952100

20962101
<scan>{G}+/_NN[^P] { yybegin(noun); yypushback(yylength()); return(next()); }
20972102
<scan>{G}+/_NNP { return(proper_name_stem()); }

0 commit comments

Comments
 (0)