Merge branch 'develop' into 'master'

Add archeopteryx

See merge request !18

.gitlab-ci.yml

@@ -53,9 +53,9 @@ build_develop:
   except:
     - master
   stage: build_develop
-  image: docker:23.0.3
+  image: docker:27.0.3
   services:
-    - "docker:23.0.3-dind"
+    - "docker:27.0.3-dind"
   script:
     - docker build -t $CI_REGISTRY_IMAGE:develop .
     - docker login -u $CI_REGISTRY_USER -p $CI_REGISTRY_PASSWORD $CI_REGISTRY
@@ -63,11 +63,11 @@ build_develop:
 
 build_master:
   stage: build_master
-  image: "docker:23.0.3"
+  image: "docker:27.0.3"
   only:
     - master
   services:
-    - "docker:23.0.3-dind"
+    - "docker:27.0.3-dind"
   script:
     - docker build -t $CI_REGISTRY_IMAGE:latest .
     - docker login -u $CI_REGISTRY_USER -p $CI_REGISTRY_PASSWORD $CI_REGISTRY

pos_tagger.yaml

@@ -16,6 +16,10 @@ taggers:
       lpmn: ["ptag"]
       output: json
       tagset: nkjp
+    archeopteryx:
+      lpmn: [{ "archeopteryx": { "mode": "chunk" } }]
+      output: json
+      tagset: nkjp
   en:
     default:
       lpmn: [{ "spacy": { "lang": "en" } }]
@@ -49,95 +53,99 @@ taggers:
 ners:
   pl:
     default:
-        lpmn: ['winer']
+      lpmn: ["winer"]
       output: json
       tagset: nkjp
-        type: 'additive'
+      type: "additive"
     spacy:
-        lpmn: [{"spacy":{"lang":"pl", 'method': 'ner'}}]
+      lpmn: [{ "spacy": { "lang": "pl", "method": "ner" } }]
       output: json
       tagset: ud
-        type: 'overwrite'
+      type: "overwrite"
     poldeepner2:
       lpmn: ["poldeepner2"]
       output: json
       tagset: nkjp
-        type: 'additive'
+      type: "additive"
     liner:
-        lpmn: [
-          'morphodita',
-          {'liner2': {'model': 'n82'}},
-          {'posconverter': {'input_format': 'ccl', 'output_format': 'json', 'ner': True}}
+      lpmn:
+        [
+          "morphodita",
+          { "liner2": { "model": "n82" } },
+          {
+            "posconverter":
+              { "input_format": "ccl", "output_format": "json", "ner": True },
+          },
         ]
       output: json
       tagset: nkjp
-        type: 'overwrite'
+      type: "overwrite"
   en:
     default:
-        lpmn: [{"spacy":{"lang":"en", 'method': 'ner'}}]
+      lpmn: [{ "spacy": { "lang": "en", "method": "ner" } }]
       output: json
       tagset: ud
-        type: 'overwrite'
+      type: "overwrite"
     poldeepner2:
       lpmn: ["poldeepner2"]
       output: json
       tagset: ud
-        type: 'additive'
+      type: "additive"
   de:
     default:
-        lpmn: [{"spacy":{"lang":"de", 'method': 'ner'}}]
+      lpmn: [{ "spacy": { "lang": "de", "method": "ner" } }]
       output: json
       tagset: ud
-        type: 'overwrite'
+      type: "overwrite"
     poldeepner2:
       lpmn: ["poldeepner2"]
       output: json
       tagset: ud
-        type: 'additive'
+      type: "additive"
   es:
     default:
-        lpmn: [{"spacy":{"lang":"es", 'method': 'ner'}}]
+      lpmn: [{ "spacy": { "lang": "es", "method": "ner" } }]
       output: json
       tagset: ud
-        type: 'overwrite'
+      type: "overwrite"
     poldeepner2:
       lpmn: ["poldeepner2"]
       output: json
       tagset: ud
-        type: 'additive'
+      type: "additive"
   pt:
     default:
-        lpmn: [{"spacy":{"lang":"pt", 'method': 'ner'}}]
+      lpmn: [{ "spacy": { "lang": "pt", "method": "ner" } }]
       output: json
       tagset: ud
-        type: 'overwrite'
+      type: "overwrite"
     poldeepner2:
       lpmn: ["poldeepner2"]
       output: json
       tagset: ud
-        type: 'additive'
+      type: "additive"
   fr:
     default:
-        lpmn: [{"spacy":{"lang":"fr", 'method': 'ner'}}]
+      lpmn: [{ "spacy": { "lang": "fr", "method": "ner" } }]
       output: json
       tagset: ud
-        type: 'overwrite'
+      type: "overwrite"
     poldeepner2:
       lpmn: ["poldeepner2"]
       output: json
       tagset: ud
-        type: 'additive'
+      type: "additive"
   ru:
     default:
-        lpmn: [{"spacy":{"lang":"ru", 'method': 'ner'}}]
+      lpmn: [{ "spacy": { "lang": "ru", "method": "ner" } }]
       output: json
       tagset: ud
-        type: 'overwrite'
+      type: "overwrite"
     poldeepner2:
       lpmn: ["poldeepner2"]
       output: json
       tagset: ud
-        type: 'additive'
+      type: "additive"
 
 linkers:
   clalink:
@@ -150,5 +158,3 @@ linkers:
     markers: ["[unused0]", "[unused1]"]
     linking_type: ["noun", "verb", "adverb", "adjective"]
     knowledge_base_id: "wordnet"
-
-