From d7030ff048fb7a6ebde3e4934f31363fdfa9fc70 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Pawe=C5=82=20Walkowiak?= <pawel.walkowiak@pwr.edu.pl>
Date: Mon, 3 Mar 2025 10:46:17 +0100
Subject: [PATCH] Update

---
 .gitlab-ci.yml  |   8 +-
 pos_tagger.yaml | 284 ++++++++++++++++++++++++------------------------
 2 files changed, 149 insertions(+), 143 deletions(-)

diff --git a/.gitlab-ci.yml b/.gitlab-ci.yml
index df4344d..8b71363 100644
--- a/.gitlab-ci.yml
+++ b/.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
diff --git a/pos_tagger.yaml b/pos_tagger.yaml
index 9432235..9c2885d 100644
--- a/pos_tagger.yaml
+++ b/pos_tagger.yaml
@@ -1,143 +1,151 @@
 taggers:
-    pl:
-      default:
-        lpmn: ["morphodita"]
-        output: ccl
-        tagset: nkjp
-      spacy:
-        lpmn: [{"spacy":{"lang":"pl"}}]
-        output: json
-        tagset: ud
-      poldeepner2tagger:
-        lpmn: ["witok", "poldeepner2tagger"]
-        output: json
-        tagset: nkjp
-      ptag:
-        lpmn: ["ptag"]
-        output: json
-        tagset: nkjp
-    en:
-      default:
-        lpmn: [{"spacy":{"lang":"en"}}]
-        output: json
-        tagset: ud
-    de:
-      default:
-        lpmn: [{"spacy":{"lang":"de"}}]
-        output: json
-        tagset: ud
-    es:
-      default:
-        lpmn: [{"spacy":{"lang":"es"}}]
-        output: json
-        tagset: ud
-    pt:
-      default:
-        lpmn: [{"spacy":{"lang":"pt"}}]
-        output: json
-        tagset: ud
-    fr:
-      default:
-        lpmn: [{"spacy":{"lang":"fr"}}]
-        output: json
-        tagset: ud
-    ru:
-      default:
-        lpmn: [{"spacy":{"lang":"ru"}}]
-        output: json
-        tagset: ud
+  pl:
+    default:
+      lpmn: ["morphodita"]
+      output: ccl
+      tagset: nkjp
+    spacy:
+      lpmn: [{ "spacy": { "lang": "pl" } }]
+      output: json
+      tagset: ud
+    poldeepner2tagger:
+      lpmn: ["witok", "poldeepner2tagger"]
+      output: json
+      tagset: nkjp
+    ptag:
+      lpmn: ["ptag"]
+      output: json
+      tagset: nkjp
+    archeopteryx:
+      lpmn: [{ "archeopteryx": { "mode": "chunk" } }]
+      output: json
+      tagset: nkjp
+  en:
+    default:
+      lpmn: [{ "spacy": { "lang": "en" } }]
+      output: json
+      tagset: ud
+  de:
+    default:
+      lpmn: [{ "spacy": { "lang": "de" } }]
+      output: json
+      tagset: ud
+  es:
+    default:
+      lpmn: [{ "spacy": { "lang": "es" } }]
+      output: json
+      tagset: ud
+  pt:
+    default:
+      lpmn: [{ "spacy": { "lang": "pt" } }]
+      output: json
+      tagset: ud
+  fr:
+    default:
+      lpmn: [{ "spacy": { "lang": "fr" } }]
+      output: json
+      tagset: ud
+  ru:
+    default:
+      lpmn: [{ "spacy": { "lang": "ru" } }]
+      output: json
+      tagset: ud
 ners:
-    pl:
-      default:
-        lpmn: ['winer']
-        output: json
-        tagset: nkjp
-        type: 'additive'
-      spacy:
-        lpmn: [{"spacy":{"lang":"pl", 'method': 'ner'}}]
-        output: json
-        tagset: ud
-        type: 'overwrite'
-      poldeepner2:
-        lpmn: ["poldeepner2"]
-        output: json
-        tagset: nkjp
-        type: 'additive'
-      liner:
-        lpmn: [
-          'morphodita',
-          {'liner2': {'model': 'n82'}},
-          {'posconverter': {'input_format': 'ccl', 'output_format': 'json', 'ner': True}}
+  pl:
+    default:
+      lpmn: ["winer"]
+      output: json
+      tagset: nkjp
+      type: "additive"
+    spacy:
+      lpmn: [{ "spacy": { "lang": "pl", "method": "ner" } }]
+      output: json
+      tagset: ud
+      type: "overwrite"
+    poldeepner2:
+      lpmn: ["poldeepner2"]
+      output: json
+      tagset: nkjp
+      type: "additive"
+    liner:
+      lpmn:
+        [
+          "morphodita",
+          { "liner2": { "model": "n82" } },
+          {
+            "posconverter":
+              { "input_format": "ccl", "output_format": "json", "ner": True },
+          },
         ]
-        output: json
-        tagset: nkjp
-        type: 'overwrite'
-    en:
-      default:
-        lpmn: [{"spacy":{"lang":"en", 'method': 'ner'}}]
-        output: json
-        tagset: ud
-        type: 'overwrite'
-      poldeepner2:
-        lpmn: ["poldeepner2"]
-        output: json
-        tagset: ud
-        type: 'additive'
-    de:
-      default:
-        lpmn: [{"spacy":{"lang":"de", 'method': 'ner'}}]
-        output: json
-        tagset: ud
-        type: 'overwrite'
-      poldeepner2:
-        lpmn: [ "poldeepner2" ]
-        output: json
-        tagset: ud
-        type: 'additive'
-    es:
-      default:
-        lpmn: [{"spacy":{"lang":"es", 'method': 'ner'}}]
-        output: json
-        tagset: ud
-        type: 'overwrite'
-      poldeepner2:
-        lpmn: [ "poldeepner2" ]
-        output: json
-        tagset: ud
-        type: 'additive'
-    pt:
-      default:
-        lpmn: [{"spacy":{"lang":"pt", 'method': 'ner'}}]
-        output: json
-        tagset: ud
-        type: 'overwrite'
-      poldeepner2:
-        lpmn: [ "poldeepner2" ]
-        output: json
-        tagset: ud
-        type: 'additive'
-    fr:
-      default:
-        lpmn: [{"spacy":{"lang":"fr", 'method': 'ner'}}]
-        output: json
-        tagset: ud
-        type: 'overwrite'
-      poldeepner2:
-        lpmn: [ "poldeepner2" ]
-        output: json
-        tagset: ud
-        type: 'additive'
-    ru:
-      default:
-        lpmn: [{"spacy":{"lang":"ru", 'method': 'ner'}}]
-        output: json
-        tagset: ud
-        type: 'overwrite'
-      poldeepner2:
-        lpmn: [ "poldeepner2" ]
-        output: json
-        tagset: ud
-        type: 'additive'
+      output: json
+      tagset: nkjp
+      type: "overwrite"
+  en:
+    default:
+      lpmn: [{ "spacy": { "lang": "en", "method": "ner" } }]
+      output: json
+      tagset: ud
+      type: "overwrite"
+    poldeepner2:
+      lpmn: ["poldeepner2"]
+      output: json
+      tagset: ud
+      type: "additive"
+  de:
+    default:
+      lpmn: [{ "spacy": { "lang": "de", "method": "ner" } }]
+      output: json
+      tagset: ud
+      type: "overwrite"
+    poldeepner2:
+      lpmn: ["poldeepner2"]
+      output: json
+      tagset: ud
+      type: "additive"
+  es:
+    default:
+      lpmn: [{ "spacy": { "lang": "es", "method": "ner" } }]
+      output: json
+      tagset: ud
+      type: "overwrite"
+    poldeepner2:
+      lpmn: ["poldeepner2"]
+      output: json
+      tagset: ud
+      type: "additive"
+  pt:
+    default:
+      lpmn: [{ "spacy": { "lang": "pt", "method": "ner" } }]
+      output: json
+      tagset: ud
+      type: "overwrite"
+    poldeepner2:
+      lpmn: ["poldeepner2"]
+      output: json
+      tagset: ud
+      type: "additive"
+  fr:
+    default:
+      lpmn: [{ "spacy": { "lang": "fr", "method": "ner" } }]
+      output: json
+      tagset: ud
+      type: "overwrite"
+    poldeepner2:
+      lpmn: ["poldeepner2"]
+      output: json
+      tagset: ud
+      type: "additive"
+  ru:
+    default:
+      lpmn: [{ "spacy": { "lang": "ru", "method": "ner" } }]
+      output: json
+      tagset: ud
+      type: "overwrite"
+    poldeepner2:
+      lpmn: ["poldeepner2"]
+      output: json
+      tagset: ud
+      type: "additive"
 
 linkers:
   clalink:
@@ -150,5 +158,3 @@ linkers:
     markers: ["[unused0]", "[unused1]"]
     linking_type: ["noun", "verb", "adverb", "adjective"]
     knowledge_base_id: "wordnet"
-
-
-- 
GitLab