msyds/gf-core
1
0
Fork 0
forked from GitHub/gf-core
Code Pull Requests Activity

Finnish VV inf forms extended with "näyttää tulevan" and "toivoo tulevansa"

Browse Source
This commit is contained in:
aarne
2013-03-31 10:03:41 +00:00
parent 700365d630
commit fbe9db8b55
8 changed files with 369 additions and 170 deletions
Download Patch File Download Diff File Expand all files Collapse all files

467
lib/src/finnish/stemmed/DictEngFin.gf
View File

File diff suppressed because it is too large Load Diff

2
lib/src/finnish/stemmed/ElimPredef.hs
View File

@@ -3,7 +3,7 @@ import qualified Data.Set as S
-- comment out words that are predefined in another lexicon
-- runghc ElimPredef.hs <DictEngFin.gf
removeFile = "todo.txt"
removeMsg = "MANUAL10"
removeMsg = "MANUALVV"
-- also used for temporarily eliminating whatever from compilation
--removeFile = "commentOut"

12
lib/src/finnish/stemmed/ParadigmsFin.gf
View File

@@ -59,6 +59,8 @@ oper
infFirst : InfForm ; -- e.g. "tehdä"
infElat : InfForm ; -- e.g. "tekemästä"
infIllat : InfForm ; -- e.g. "tekemään"
infPresPart : InfForm ; -- e.g. "tekevän"
infPresPartAgr : InfForm ; -- e.g. "tekevänsä"
-- The following type is used for defining *rection*, i.e. complements
-- of many-place verbs and adjective. A complement can be defined by
@@ -228,10 +230,14 @@ oper
-- questions, verb phrases, and adjectives.
mkVV = overload {
mkVV : Str -> VV -- e.g. "yrittää"
mkVV : Str -> VV -- e.g. "yrittää" (puhua)
= \s -> mkVVf (mkV s) infFirst ;
mkVV : V -> VV -- e.g. "alkaa"
mkVV : V -> VV -- e.g. "alkaa" (puhua)
= \v -> mkVVf v infFirst ;
mkVV : Str -> InfForm -> VV -- e.g. "ruveta" (puhumaan)
= \s,i -> mkVVf (mkV s) i ;
mkVV : V -> InfForm -> VV -- e.g. "lakata" (puhumasta)
= \v,i -> mkVVf v i ;
} ;
mkVS = overload {
@@ -313,7 +319,7 @@ mkVS = overload {
ablative = Ablat ;
allative = Allat ;
infFirst = Inf1 ; infElat = Inf3Elat ; infIllat = Inf3Illat ;
infFirst = Inf1 ; infElat = Inf3Elat ; infIllat = Inf3Illat ; infPresPart = InfPresPart ; infPresPartAgr = InfPresPartAgr ;
prePrep : Case -> Str -> Prep =
\c,p -> {c = NPCase c ; s = p ; isPre = True ; lock_Prep = <>} ;

6
lib/src/finnish/stemmed/StemFin.gf
View File

@@ -192,6 +192,8 @@ oper
tullun = plus tullu_ "n" ;
tultu = plus tult_ u ;
tuleva = plus tule_ ("v" + a) ;
tullutN : Noun = snoun2noun b {
s = table SNForm [
tullut ;
@@ -270,7 +272,9 @@ oper
Inf Inf3Elat => plus tulema ("st" + a) ;
Inf Inf3Illat => plus tulema (a + "n") ;
Inf Inf3Adess => plus tulema ("ll" + a) ;
Inf Inf3Abess => plus tulema ("tt" + a)
Inf Inf3Abess => plus tulema ("tt" + a) ;
Inf InfPresPart => plus tuleva "n" ;
Inf InfPresPartAgr => tuleva
} ;
sc = NPCase Nom ;
lock_V = <>

1
lib/src/finnish/stemmed/WNKotus.gf
View File

@@ -81,6 +81,7 @@ oper
mkWVV = overload {
mkWVV : (_ : Str) -> VV = \s -> mkVV (mkV s) ;
mkWVV : (_ : VForms) -> VV = \vf -> mkVV (mkV (lin VK {s = vf})) ;
mkWVV : (_ : VForms) -> InfForm -> VV = \vf,i -> mkVV (mkV (lin VK {s = vf})) i ;
mkWVV : (_ : V) -> VV = \v -> mkVV v ;
mkWVV : VForms -> Str -> VV = \vf,s -> mkVV (mkV (mkV (lin VK {s = vf})) s) ;
} ;

9
lib/src/finnish/stemmed/log.txt
View File

@@ -115,12 +115,19 @@ Spent 30 minutes going through 230 10+ words. Changed a half of them. Some ARBIT
business language (e.g. "officer", "upseeri"/"vastaava"?). This changed 1362 sentences.
Now, after 2 days of work, we have version 10-, where 2700 translations have changed from version 1-. Spent approximately
- 2 hours manually correcting the lexicon
- 3 hours manually correcting the lexicon
- 5 hours analysing the problems and designing analysis tools
- 8 hours fixing RGL bugs
31/3
Dictionary revision: 250 words with 6--10 occurrences ; 107 changed in 30 minutes. Changes in 557 sentences.
RGL fix: more infinitive forms (näyttää nukkuvan, toivoo nukkuvansa); forms available through mkVV.
Checked 50 VV's in Dict. 145 changes in translations.