Update specificity rule matching for annotations
Change-Id: Ifa7ec5eef3583cb196f4aa1ca0cfcd65790de226
diff --git a/mappings/stts-upos.yaml b/mappings/stts-upos.yaml
index df5eebb..24a7fc2 100644
--- a/mappings/stts-upos.yaml
+++ b/mappings/stts-upos.yaml
@@ -59,4 +59,19 @@
- "[VVIZU] <> [VERB & VerbForm=Inf]"
- "[VVPP] <> [VERB & Aspect=Perf & VerbForm=Part]"
- "[XY] <> [X]"
+ # Fallback rules for bare UPoS tags (less specific, selected only when no
+ # more-specific rule matches)
+ - "[ADJA | ADJD] <> [ADJ]"
+ - "[ART | PDAT | PIAT | PIDAT | PPOSAT | PRELAT | PWAT] <> [DET]"
+ - "[KOUI | KOUS] <> [SCONJ]"
+ - "[VVFIN | VVIMP | VVINF | VVIZU | VVPP | VMFIN | VMINF | VMPP] <> [VERB]"
+ - "[VAFIN | VAIMP | VAINF | VAPP] <> [AUX]"
+ - "[APPO | APPR | APPRART | APZR | PTKVZ] <> [ADP]"
+ - "[PDS | PIS | PPER | PPOSS | PRELS | PRF | PWS] <> [PRON]"
+ - "[PTKA | PTKANT | PTKNEG | PTKZU] <> [PART]"
+ - "[FM | TRUNC | XY] <> [X]"
+ - "[$\\( | $, | $.] <> [PUNCT]"
+ - "[KON | KOKOM] <> [CCONJ]"
+ - "[ADV | PAV | PWAV] <> [ADV]"
+ - "[NN | NE] <> [NOUN | PROPN]"
diff --git a/mappings/wiki-dereko.yaml b/mappings/wiki-dereko.yaml
index 83b4815..712f29a 100644
--- a/mappings/wiki-dereko.yaml
+++ b/mappings/wiki-dereko.yaml
@@ -78,13 +78,13 @@
- "Technology <> (wissenschaft & populaerwissenschaft)"
# Universe (1967 files): wissenschaft.populaerwissenschaft=41.1%
- "Universe <> (wissenschaft & populaerwissenschaft)"
- # freizeit-unterhaltung.reisen → History, Geography, Culture (AND)
+ # freizeit-unterhaltung.reisen -> History, Geography, Culture (AND)
- "(History | Geography | Culture) <> (freizeit-unterhaltung & reisen)"
- # technik-industrie.edv-elektronik → Entities, Internet (AND)
+ # technik-industrie.edv-elektronik -> Entities, Internet (AND)
- "(Entities | Internet) <> (technik-industrie & edv-elektronik)"
- # kultur.literatur → Language, History (AND)
+ # kultur.literatur -> Language, History (AND)
- "(Language | History) <> (kultur & literatur)"
- # politik.ausland → Law, Military (AND)
+ # politik.ausland -> Law, Military (AND)
- "(Law | Military) <> (politik & ausland)"
# Health (1952 files): gesundheit-ernaehrung.gesundheit=28.7%
- "Health <> (gesundheit-ernaehrung & gesundheit)"