Merge pull request #1320 from dkpro/bugfix/858-Out-of-tagset-tags-sho…

…uld-map-to-the-generic-type #858 - Out-of-tagset tags should map to the generic type
dkpro · Jan 15, 2019 · fd902c0 · fd902c0
2 parents 7beaef2 + 93dc360
commit fd902c0
Show file tree

Hide file tree

Showing 26 changed files with 57 additions and 89 deletions.
diff --git a/...asl/src/main/resources/de/tudarmstadt/ukp/dkpro/core/api/lexmorph/tagset/bn-utpal-pos.map b/...asl/src/main/resources/de/tudarmstadt/ukp/dkpro/core/api/lexmorph/tagset/bn-utpal-pos.map
@@ -43,5 +43,5 @@ SYM=POS_SYM
 RDP=POS_X
 # UNK  Unknown
 UNK=POS_X
-*=POS_X
+*=POS
 
diff --git a/...-asl/src/main/resources/de/tudarmstadt/ukp/dkpro/core/api/lexmorph/tagset/de-stts-pos.map b/...-asl/src/main/resources/de/tudarmstadt/ukp/dkpro/core/api/lexmorph/tagset/de-stts-pos.map
@@ -12,7 +12,7 @@ __META_SOURCE_URL__=http://www.ims.uni-stuttgart.de/forschung/ressourcen/lexika/
 __META_TYPE_BASE__=de.tudarmstadt.ukp.dkpro.core.api.lexmorph.type.pos.
 
 # Catch-all rule
-*=POS_X
+*=POS
 #
 # $*LRB* 
 # -

diff --git a/...ain/resources/de/tudarmstadt/ukp/dkpro/core/api/lexmorph/tagset/de-tiger-rftagger-pos.map b/...ain/resources/de/tudarmstadt/ukp/dkpro/core/api/lexmorph/tagset/de-tiger-rftagger-pos.map
@@ -38,4 +38,4 @@ VINF=POS_VERB
 SYM=POS_PUNCT
 SENT=POS_PUNCT
 
-*=POS_X
+*=POS
diff --git a/.../src/main/resources/de/tudarmstadt/ukp/dkpro/core/api/lexmorph/tagset/en-arktweet-pos.map b/.../src/main/resources/de/tudarmstadt/ukp/dkpro/core/api/lexmorph/tagset/en-arktweet-pos.map
@@ -3,7 +3,7 @@ __META_TYPE_BASE__=de.tudarmstadt.ukp.dkpro.core.api.lexmorph.type.pos.
 
 $=POS_NUM
 &=POS_CONJ
-*=POS_X
+*=POS
 ,=POS_PUNCT
 @=tweet.POS_AT
 A=POS_ADJ

diff --git a/...asl/src/main/resources/de/tudarmstadt/ukp/dkpro/core/api/lexmorph/tagset/en-brown-pos.map b/...asl/src/main/resources/de/tudarmstadt/ukp/dkpro/core/api/lexmorph/tagset/en-brown-pos.map
@@ -10,7 +10,7 @@ __META_TYPE_BASE__=de.tudarmstadt.ukp.dkpro.core.api.lexmorph.type.pos.
 # right paren
 )=POS_X
 # not, n't
-#*=POS_X
+#*=POS
 # dash
 -=POS_X
 # comma
@@ -185,4 +185,4 @@ NEG=POS_ADV
 NNSG=POS_NOUN
 NR$=POS_NOUN
 
-*=POS_X
+*=POS
diff --git a/.../src/main/resources/de/tudarmstadt/ukp/dkpro/core/api/lexmorph/tagset/en-browntei-pos.map b/.../src/main/resources/de/tudarmstadt/ukp/dkpro/core/api/lexmorph/tagset/en-browntei-pos.map
@@ -86,4 +86,4 @@ NRg=POS_NOUN
 RBT=POS_ADV
 UH=POS_PART
 WQL=POS_ADV
-*=POS_X
+*=POS
diff --git a/...ph-asl/src/main/resources/de/tudarmstadt/ukp/dkpro/core/api/lexmorph/tagset/en-c5-pos.map b/...ph-asl/src/main/resources/de/tudarmstadt/ukp/dkpro/core/api/lexmorph/tagset/en-c5-pos.map
@@ -6,7 +6,7 @@ __META_SOURCE_URL__=http://www.natcorp.ox.ac.uk/docs/gramtag.html
 __META_TYPE_BASE__=de.tudarmstadt.ukp.dkpro.core.api.lexmorph.type.pos.
 
 # Default mapping
-*=POS_X
+*=POS
 
 # AJ0	Adjective (general or positive) (e.g. good, old, beautiful)
 AJ0=POS_ADJ

diff --git a/...h-asl/src/main/resources/de/tudarmstadt/ukp/dkpro/core/api/lexmorph/tagset/en-lbj-pos.map b/...h-asl/src/main/resources/de/tudarmstadt/ukp/dkpro/core/api/lexmorph/tagset/en-lbj-pos.map
@@ -5,7 +5,7 @@
 
 __META_TYPE_BASE__=de.tudarmstadt.ukp.dkpro.core.api.lexmorph.type.pos.
 
-*=POS_X
+*=POS
 # punctuation mark, comma
 ,=POS_PUNCT
 -=POS_PUNCT

diff --git a/...l/src/main/resources/de/tudarmstadt/ukp/dkpro/core/api/lexmorph/tagset/en-medpost-pos.map b/...l/src/main/resources/de/tudarmstadt/ukp/dkpro/core/api/lexmorph/tagset/en-medpost-pos.map
@@ -124,4 +124,4 @@ VVGN=POS_VERB
 # ” right quote 
 ''=POS_PUNCT
 
-*=POS_X
+*=POS
diff --git a/...src/main/resources/de/tudarmstadt/ukp/dkpro/core/api/lexmorph/tagset/en-ptb-emory-pos.map b/...src/main/resources/de/tudarmstadt/ukp/dkpro/core/api/lexmorph/tagset/en-ptb-emory-pos.map
@@ -7,7 +7,7 @@
 
 __META_TYPE_BASE__=de.tudarmstadt.ukp.dkpro.core.api.lexmorph.type.pos.
 
-*=POS_X
+*=POS
 # punctuation mark, comma
 ,=POS_PUNCT
 -=POS_PUNCT

diff --git a/...sl/src/main/resources/de/tudarmstadt/ukp/dkpro/core/api/lexmorph/tagset/en-ptb-tt-pos.map b/...sl/src/main/resources/de/tudarmstadt/ukp/dkpro/core/api/lexmorph/tagset/en-ptb-tt-pos.map
@@ -5,7 +5,7 @@
 __META_SOURCE_URL__=http://faculty.washington.edu/dillon/GramResources/penntable.html
 __META_TYPE_BASE__=de.tudarmstadt.ukp.dkpro.core.api.lexmorph.type.pos.
 
-*=POS_X
+*=POS
 ,=POS_PUNCT
 -=POS_PUNCT
 .=POS_PUNCT

diff --git a/...src/main/resources/de/tudarmstadt/ukp/dkpro/core/api/lexmorph/tagset/es-conll2009-pos.map b/...src/main/resources/de/tudarmstadt/ukp/dkpro/core/api/lexmorph/tagset/es-conll2009-pos.map
@@ -5,7 +5,7 @@
 __META_SOURCE_URL__=http://clic.ub.edu/corpus/webfm_send/18
 __META_TYPE_BASE__=de.tudarmstadt.ukp.dkpro.core.api.lexmorph.type.pos.
 
-*=POS_X
+*=POS
 #Adjective
 a=POS_ADJ
 #Conjuction

diff --git a/...asl/src/main/resources/de/tudarmstadt/ukp/dkpro/core/api/lexmorph/tagset/et-tartu-pos.map b/...asl/src/main/resources/de/tudarmstadt/ukp/dkpro/core/api/lexmorph/tagset/et-tartu-pos.map
@@ -584,4 +584,4 @@ Z.Osq=POS_PUNCT
 Z.Csq=POS_PUNCT
 Z.Sla=POS_PUNCT
 T=POS_X
-*=POS_X
+*=POS
diff --git a/...h-asl/src/main/resources/de/tudarmstadt/ukp/dkpro/core/api/lexmorph/tagset/fa-upc-pos.map b/...h-asl/src/main/resources/de/tudarmstadt/ukp/dkpro/core/api/lexmorph/tagset/fa-upc-pos.map
@@ -67,5 +67,5 @@ V_COP=POS_VERB
 V_PRS=POS_VERB
 # V_SUB - Subjunctive verb
 V_SUB=POS_VERB
-*=POS_X
+*=POS
 
diff --git a/...c/main/resources/de/tudarmstadt/ukp/dkpro/core/api/lexmorph/tagset/fa-upc-reduced-pos.map b/...c/main/resources/de/tudarmstadt/ukp/dkpro/core/api/lexmorph/tagset/fa-upc-reduced-pos.map
@@ -39,4 +39,4 @@ STPOS=POS_X
 STR=POS_X
 # V - Verb
 V=POS_VERB
-*=POS_X
+*=POS
diff --git a/...h-asl/src/main/resources/de/tudarmstadt/ukp/dkpro/core/api/lexmorph/tagset/fr-ftb-pos.map b/...h-asl/src/main/resources/de/tudarmstadt/ukp/dkpro/core/api/lexmorph/tagset/fr-ftb-pos.map
@@ -35,4 +35,4 @@ PUNC=POS_PUNCT
 \:=POS_PUNCT
 # V
 V=POS_VERB
-*=POS_X
+*=POS
diff --git a/...asl/src/main/resources/de/tudarmstadt/ukp/dkpro/core/api/lexmorph/tagset/fr-stein-pos.map b/...asl/src/main/resources/de/tudarmstadt/ukp/dkpro/core/api/lexmorph/tagset/fr-stein-pos.map
@@ -7,7 +7,7 @@
 __META_SOURCE_URL__=http://www.ims.uni-stuttgart.de/~schmid/french-tagset.html
 __META_TYPE_BASE__=de.tudarmstadt.ukp.dkpro.core.api.lexmorph.type.pos.
 
-*=POS_X
+*=POS
 # ABR	abreviation
 ABR=POS_X
 # ADJ	adjective

diff --git a/...asl/src/main/resources/de/tudarmstadt/ukp/dkpro/core/api/lexmorph/tagset/it-stein-pos.map b/...asl/src/main/resources/de/tudarmstadt/ukp/dkpro/core/api/lexmorph/tagset/it-stein-pos.map
@@ -7,7 +7,7 @@
 __META_SOURCE_URL__=ftp://ftp.ims.uni-stuttgart.de/pub/corpora/italian-tagset.txt
 __META_TYPE_BASE__=de.tudarmstadt.ukp.dkpro.core.api.lexmorph.type.pos.
 
-*=POS_X
+*=POS
 # ABR	abbreviation
 ABR=POS_X
 # ADJ	adjective

diff --git a/...-asl/src/main/resources/de/tudarmstadt/ukp/dkpro/core/api/lexmorph/tagset/it-tanl-pos.map b/...-asl/src/main/resources/de/tudarmstadt/ukp/dkpro/core/api/lexmorph/tagset/it-tanl-pos.map
@@ -5,7 +5,7 @@
 __META_SOURCE_URL__=Source: http://medialab.di.unipi.it/wiki/Tanl_POS_Tagset
 __META_TYPE_BASE__=de.tudarmstadt.ukp.dkpro.core.api.lexmorph.type.pos.
 
-*=POS_X
+*=POS
 APn=POS_ADJ
 APp=POS_ADJ
 APs=POS_ADJ

diff --git a/...morph-asl/src/main/resources/de/tudarmstadt/ukp/dkpro/core/api/lexmorph/tagset/ru-pos.map b/...morph-asl/src/main/resources/de/tudarmstadt/ukp/dkpro/core/api/lexmorph/tagset/ru-pos.map
@@ -1,5 +1,5 @@
 __META_TYPE_BASE__=de.tudarmstadt.ukp.dkpro.core.api.lexmorph.type.pos.
-*=POS_X
+*=POS
 A-NUM=POS_ADJ
 A-PRO=POS_PRON
 A=POS_ADJ

diff --git a/...h-asl/src/main/resources/de/tudarmstadt/ukp/dkpro/core/api/lexmorph/tagset/sv-suc-pos.map b/...h-asl/src/main/resources/de/tudarmstadt/ukp/dkpro/core/api/lexmorph/tagset/sv-suc-pos.map
@@ -62,4 +62,4 @@ MID=POS_PUNCT
 PAD=POS_PUNCT
 
 # Catch-all rule
-*=POS_X
+*=POS
diff --git a/...h-asl/src/main/resources/de/tudarmstadt/ukp/dkpro/core/api/lexmorph/tagset/zh-ctb-pos.map b/...h-asl/src/main/resources/de/tudarmstadt/ukp/dkpro/core/api/lexmorph/tagset/zh-ctb-pos.map
@@ -75,4 +75,4 @@ VV=POS_VERB
 # X
 X=POS_X
 
-*=POS_X
+*=POS
diff --git a/...-asl/src/main/resources/de/tudarmstadt/ukp/dkpro/core/api/lexmorph/tagset/zh-lcmc-pos.map b/...-asl/src/main/resources/de/tudarmstadt/ukp/dkpro/core/api/lexmorph/tagset/zh-lcmc-pos.map
@@ -6,7 +6,7 @@ __META_SOURCE_URL__=http://www.lancs.ac.uk/fass/projects/corpus/LCMC/lcmc/lcmc_t
 __META_TYPE_BASE__=de.tudarmstadt.ukp.dkpro.core.api.lexmorph.type.pos.
 
 # Catch-all rule
-*=POS_X
+*=POS
 
 # a          adjective
 a=POS_ADJ

diff --git a/...-core-hunpos-asl/src/test/java/de/tudarmstadt/ukp/dkpro/core/hunpos/HunPosTaggerTest.java b/...-core-hunpos-asl/src/test/java/de/tudarmstadt/ukp/dkpro/core/hunpos/HunPosTaggerTest.java
@@ -169,7 +169,7 @@ public void testSwedish()
         runTest("sv", null, "Detta är ett test .",
                 new String[] { "PN_NEU_SIN_DEF_SUB/OBJ", "VB_PRS_AKT", "DT_NEU_SIN_IND",
                         "NN_NEU_SIN_IND_NOM", "DL_MAD" },
-                new String[] { "POS_X", "POS_X", "POS_X", "POS_X", "POS_X" });
+                new String[] { "POS", "POS", "POS", "POS", "POS" });
 
         runTest("sv", "paroletags", "Detta är ett test .",
                 new String[] { "PF@NS0@S", "V@IPAS", "DI@NS@S", "NCNSN@IS", "FE" },
@@ -178,7 +178,7 @@ public void testSwedish()
         runTest("sv", "suctags", "Detta är ett test .",
                 new String[] { "PN_NEU_SIN_DEF_SUB/OBJ", "VB_PRS_AKT", "DT_NEU_SIN_IND",
                         "NN_NEU_SIN_IND_NOM", "DL_MAD" },
-                new String[] { "POS_X", "POS_X", "POS_X", "POS_X", "POS_X" });
+                new String[] { "POS", "POS", "POS", "POS", "POS" });
 
         // runTest("sv", "suc2x", "Detta är ett test .",
         // new String[] { "PN_NEU_SIN_DEF_SUB@OBJ", "VB_PRS_AKT", "DT_NEU_SIN_IND",