Update spaCy pipeline

README.md

@@ -14,48 +14,48 @@ model-index:
     metrics:
     - name: NER Precision
       type: precision
-      value: 0.7714191745
+      value: 0.7701563395
     - name: NER Recall
       type: recall
-      value: 0.6628046627
+      value: 0.6647121159
     - name: NER F Score
       type: f_score
-      value: 0.712999202
+      value: 0.7135598362
   - task:
       name: TAG
       type: token-classification
     metrics:
     - name: TAG (XPOS) Accuracy
       type: accuracy
-      value: 0.7335983702
+      value: 0.7320951759
   - task:
       name: POS
       type: token-classification
     metrics:
     - name: POS (UPOS) Accuracy
       type: accuracy
-      value: 0.8608501296
+      value: 0.860041932
   - task:
       name: LEMMA
       type: token-classification
     metrics:
     - name: Lemma Accuracy
       type: accuracy
-      value: 0.8317806919
+      value: 0.8340354833
   - task:
       name: UNLABELED_DEPENDENCIES
       type: token-classification
     metrics:
     - name: Unlabeled Attachment Score (UAS)
       type: f_score
-      value: 0.7375785393
+      value: 0.7420346687
   - task:
       name: LABELED_DEPENDENCIES
       type: token-classification
     metrics:
     - name: Labeled Attachment Score (LAS)
       type: f_score
-      value: 0.6555857582
+      value: 0.6614531114
   - task:
       name: SENTS
       type: token-classification
@@ -71,8 +71,8 @@ Korean pipeline optimized for CPU. Components: tok2vec, tagger, morphologizer, p
 | Feature | Description |
 | --- | --- |
 | **Name** | `ko_core_news_sm` |
-| **Version** | `3.3.0` |
-| **spaCy** | `>=3.3.0.dev0,<3.4.0` |
+| **Version** | `3.4.0` |
+| **spaCy** | `>=3.4.0,<3.5.0` |
 | **Default Pipeline** | `tok2vec`, `tagger`, `morphologizer`, `parser`, `lemmatizer`, `attribute_ruler`, `ner` |
 | **Components** | `tok2vec`, `tagger`, `morphologizer`, `parser`, `lemmatizer`, `senter`, `attribute_ruler`, `ner` |
 | **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
@@ -84,12 +84,12 @@ Korean pipeline optimized for CPU. Components: tok2vec, tagger, morphologizer, p
 
 <details>
 
-<summary>View label scheme (2026 labels for 4 components)</summary>
+<summary>View label scheme (2028 labels for 4 components)</summary>
 
 | Component | Labels |
 | --- | --- |
-| **`tagger`** | `ecs`, `etm`, `f`, `f+f+jcj`, `f+f+jcs`, `f+f+jct`, `f+f+jxt`, `f+jca`, `f+jca+jp+ecc`, `f+jca+jp+ep+ef`, `f+jca+jxc`, `f+jca+jxc+jcm`, `f+jca+jxt`, `f+jcj`, `f+jcm`, `f+jco`, `f+jcs`, `f+jct`, `f+jct+jcm`, `f+jp+ef`, `f+jp+ep+ef`, `f+jp+etm`, `f+jxc`, `f+jxt`, `f+ncn`, `f+ncn+jcm`, `f+ncn+jcs`, `f+ncn+jp+ecc`, `f+ncn+jxt`, `f+ncpa+jcm`, `f+npp+jcs`, `f+nq`, `f+xsn`, `f+xsn+jco`, `f+xsn+jxt`, `ii`, `jca`, `jca+jcm`, `jca+jxc`, `jca+jxt`, `jcc`, `jcj`, `jcm`, `jco`, `jcr`, `jcr+jxc`, `jcs`, `jct`, `jct+jcm`, `jct+jxt`, `jp+ecc`, `jp+ecs`, `jp+ef`, `jp+ef+jcr`, `jp+ef+jcr+jxc`, `jp+ep+ecs`, `jp+ep+ef`, `jp+ep+etm`, `jp+ep+etn`, `jp+etm`, `jp+etn`, `jp+etn+jco`, `jp+etn+jxc`, `jxc`, `jxc+jca`, `jxc+jco`, `jxc+jcs`, `jxt`, `mad`, `mad+jxc`, `mad+jxt`, `mag`, `mag+jca`, `mag+jcm`, `mag+jcs`, `mag+jp+ef+jcr`, `mag+jxc`, `mag+jxc+jxc`, `mag+jxt`, `mag+xsn`, `maj`, `maj+jxc`, `maj+jxt`, `mma`, `mmd`, `nbn`, `nbn+jca`, `nbn+jca+jcj`, `nbn+jca+jcm`, `nbn+jca+jp+ef`, `nbn+jca+jxc`, `nbn+jca+jxt`, `nbn+jcc`, `nbn+jcj`, `nbn+jcm`, `nbn+jco`, `nbn+jcr`, `nbn+jcs`, `nbn+jct`, `nbn+jct+jcm`, `nbn+jct+jxt`, `nbn+jp+ecc`, `nbn+jp+ecs`, `nbn+jp+ecs+jca`, `nbn+jp+ecs+jcm`, `nbn+jp+ecs+jco`, `nbn+jp+ecs+jxc`, `nbn+jp+ecs+jxt`, `nbn+jp+ecx`, `nbn+jp+ef`, `nbn+jp+ef+jca`, `nbn+jp+ef+jco`, `nbn+jp+ef+jcr`, `nbn+jp+ef+jcr+jxc`, `nbn+jp+ef+jcr+jxt`, `nbn+jp+ef+jcs`, `nbn+jp+ef+jxc`, `nbn+jp+ef+jxc+jco`, `nbn+jp+ef+jxf`, `nbn+jp+ef+jxt`, `nbn+jp+ep+ecc`, `nbn+jp+ep+ecs`, `nbn+jp+ep+ecs+jxc`, `nbn+jp+ep+ef`, `nbn+jp+ep+ef+jcr`, `nbn+jp+ep+etm`, `nbn+jp+ep+etn`, `nbn+jp+ep+etn+jco`, `nbn+jp+ep+etn+jcs`, `nbn+jp+etm`, `nbn+jp+etn`, `nbn+jp+etn+jca`, `nbn+jp+etn+jca+jxt`, `nbn+jp+etn+jco`, `nbn+jp+etn+jcs`, `nbn+jp+etn+jxc`, `nbn+jp+etn+jxt`, `nbn+jxc`, `nbn+jxc+jca`, `nbn+jxc+jca+jxc`, `nbn+jxc+jca+jxt`, `nbn+jxc+jcc`, `nbn+jxc+jcm`, `nbn+jxc+jco`, `nbn+jxc+jcs`, `nbn+jxc+jp+ef`, `nbn+jxc+jxc`, `nbn+jxc+jxt`, `nbn+jxt`, `nbn+nbn`, `nbn+nbn+jp+ef`, `nbn+xsm+ecs`, `nbn+xsm+ef`, `nbn+xsm+ep+ef`, `nbn+xsm+ep+ef+jcr`, `nbn+xsm+etm`, `nbn+xsn`, `nbn+xsn+jca`, `nbn+xsn+jca+jp+ef+jcr`, `nbn+xsn+jca+jxc`, `nbn+xsn+jca+jxt`, `nbn+xsn+jcm`, `nbn+xsn+jco`, `nbn+xsn+jcs`, `nbn+xsn+jct`, `nbn+xsn+jp+ecc`, `nbn+xsn+jp+ecs`, `nbn+xsn+jp+ef`, `nbn+xsn+jp+ef+jcr`, `nbn+xsn+jp+ep+ef`, `nbn+xsn+jxc`, `nbn+xsn+jxt`, `nbn+xsv+etm`, `nbu`, `nbu+jca`, `nbu+jca+jxc`, `nbu+jca+jxt`, `nbu+jcc`, `nbu+jcc+jxc`, `nbu+jcj`, `nbu+jcm`, `nbu+jco`, `nbu+jcs`, `nbu+jct`, `nbu+jct+jxc`, `nbu+jp+ecc`, `nbu+jp+ecs`, `nbu+jp+ef`, `nbu+jp+ef+jcr`, `nbu+jp+ef+jxc`, `nbu+jp+ep+ecc`, `nbu+jp+ep+ecs`, `nbu+jp+ep+ef`, `nbu+jp+ep+ef+jcr`, `nbu+jp+ep+etm`, `nbu+jp+ep+etn+jco`, `nbu+jp+etm`, `nbu+jxc`, `nbu+jxc+jca`, `nbu+jxc+jcs`, `nbu+jxc+jp+ef`, `nbu+jxc+jp+ep+ef`, `nbu+jxc+jxt`, `nbu+jxt`, `nbu+ncn`, `nbu+ncn+jca`, `nbu+ncn+jcm`, `nbu+xsn`, `nbu+xsn+jca`, `nbu+xsn+jca+jxc`, `nbu+xsn+jca+jxt`, `nbu+xsn+jcm`, `nbu+xsn+jco`, `nbu+xsn+jcs`, `nbu+xsn+jp+ecs`, `nbu+xsn+jp+ep+ef`, `nbu+xsn+jxc`, `nbu+xsn+jxc+jxt`, `nbu+xsn+jxt`, `nbu+xsv+ecc`, `nbu+xsv+etm`, `ncn`, `ncn+f+ncpa+jco`, `ncn+jca`, `ncn+jca+jca`, `ncn+jca+jcc`, `ncn+jca+jcj`, `ncn+jca+jcm`, `ncn+jca+jcs`, `ncn+jca+jct`, `ncn+jca+jp+ecc`, `ncn+jca+jp+ecs`, `ncn+jca+jp+ef`, `ncn+jca+jp+ep+ef`, `ncn+jca+jp+etm`, `ncn+jca+jp+etn+jxt`, `ncn+jca+jxc`, `ncn+jca+jxc+jcc`, `ncn+jca+jxc+jcm`, `ncn+jca+jxc+jxc`, `ncn+jca+jxc+jxt`, `ncn+jca+jxt`, `ncn+jcc`, `ncn+jcc+jxc`, `ncn+jcj`, `ncn+jcj+jxt`, `ncn+jcm`, `ncn+jco`, `ncn+jcr`, `ncn+jcr+jxc`, `ncn+jcs`, `ncn+jcs+jxt`, `ncn+jct`, `ncn+jct+jcm`, `ncn+jct+jxc`, `ncn+jct+jxt`, `ncn+jcv`, `ncn+jp+ecc`, `ncn+jp+ecc+jct`, `ncn+jp+ecc+jxc`, `ncn+jp+ecs`, `ncn+jp+ecs+jcm`, `ncn+jp+ecs+jco`, `ncn+jp+ecs+jxc`, `ncn+jp+ecs+jxt`, `ncn+jp+ecx`, `ncn+jp+ef`, `ncn+jp+ef+jca`, `ncn+jp+ef+jcm`, `ncn+jp+ef+jco`, `ncn+jp+ef+jcr`, `ncn+jp+ef+jcr+jxc`, `ncn+jp+ef+jcr+jxt`, `ncn+jp+ef+jp+etm`, `ncn+jp+ef+jxc`, `ncn+jp+ef+jxf`, `ncn+jp+ef+jxt`, `ncn+jp+ep+ecc`, `ncn+jp+ep+ecs`, `ncn+jp+ep+ecs+jxc`, `ncn+jp+ep+ecx`, `ncn+jp+ep+ef`, `ncn+jp+ep+ef+jcr`, `ncn+jp+ep+ef+jcr+jxc`, `ncn+jp+ep+ef+jxc`, `ncn+jp+ep+ef+jxf`, `ncn+jp+ep+ef+jxt`, `ncn+jp+ep+ep+etm`, `ncn+jp+ep+etm`, `ncn+jp+ep+etn`, `ncn+jp+ep+etn+jca`, `ncn+jp+ep+etn+jca+jxc`, `ncn+jp+ep+etn+jco`, `ncn+jp+ep+etn+jcs`, `ncn+jp+ep+etn+jxt`, `ncn+jp+etm`, `ncn+jp+etn`, `ncn+jp+etn+jca`, `ncn+jp+etn+jca+jxc`, `ncn+jp+etn+jca+jxt`, `ncn+jp+etn+jco`, `ncn+jp+etn+jcs`, `ncn+jp+etn+jct`, `ncn+jp+etn+jxc`, `ncn+jp+etn+jxt`, `ncn+jxc`, `ncn+jxc+jca`, `ncn+jxc+jca+jxc`, `ncn+jxc+jca+jxt`, `ncn+jxc+jcc`, `ncn+jxc+jcm`, `ncn+jxc+jco`, `ncn+jxc+jcs`, `ncn+jxc+jct+jxt`, `ncn+jxc+jp+ef`, `ncn+jxc+jp+ef+jcr`, `ncn+jxc+jp+ep+ecs`, `ncn+jxc+jp+ep+ef`, `ncn+jxc+jp+etm`, `ncn+jxc+jxc`, `ncn+jxc+jxt`, `ncn+jxt`, `ncn+jxt+jcm`, `ncn+jxt+jxc`, `ncn+nbn`, `ncn+nbn+jca`, `ncn+nbn+jcm`, `ncn+nbn+jcs`, `ncn+nbn+jp+ecc`, `ncn+nbn+jp+ep+ef`, `ncn+nbn+jxc`, `ncn+nbn+jxt`, `ncn+nbu`, `ncn+nbu+jca`, `ncn+nbu+jcm`, `ncn+nbu+jco`, `ncn+nbu+jp+ef`, `ncn+nbu+jxc`, `ncn+nbu+ncn`, `ncn+ncn`, `ncn+ncn+jca`, `ncn+ncn+jca+jcc`, `ncn+ncn+jca+jcm`, `ncn+ncn+jca+jxc`, `ncn+ncn+jca+jxc+jcm`, `ncn+ncn+jca+jxc+jxc`, `ncn+ncn+jca+jxt`, `ncn+ncn+jcc`, `ncn+ncn+jcj`, `ncn+ncn+jcm`, `ncn+ncn+jco`, `ncn+ncn+jcr`, `ncn+ncn+jcs`, `ncn+ncn+jct`, `ncn+ncn+jct+jcm`, `ncn+ncn+jct+jxc`, `ncn+ncn+jct+jxt`, `ncn+ncn+jp+ecc`, `ncn+ncn+jp+ecs`, `ncn+ncn+jp+ef`, `ncn+ncn+jp+ef+jcm`, `ncn+ncn+jp+ef+jcr`, `ncn+ncn+jp+ef+jcs`, `ncn+ncn+jp+ep+ecc`, `ncn+ncn+jp+ep+ecs`, `ncn+ncn+jp+ep+ef`, `ncn+ncn+jp+ep+ef+jcr`, `ncn+ncn+jp+ep+ep+etm`, `ncn+ncn+jp+ep+etm`, `ncn+ncn+jp+ep+etn`, `ncn+ncn+jp+etm`, `ncn+ncn+jp+etn`, `ncn+ncn+jp+etn+jca`, `ncn+ncn+jp+etn+jco`, `ncn+ncn+jp+etn+jxc`, `ncn+ncn+jxc`, `ncn+ncn+jxc+jca`, `ncn+ncn+jxc+jcc`, `ncn+ncn+jxc+jcm`, `ncn+ncn+jxc+jco`, `ncn+ncn+jxc+jcs`, `ncn+ncn+jxc+jxc`, `ncn+ncn+jxt`, `ncn+ncn+nbn`, `ncn+ncn+ncn`, `ncn+ncn+ncn+jca`, `ncn+ncn+ncn+jca+jcm`, `ncn+ncn+ncn+jca+jxt`, `ncn+ncn+ncn+jcj`, `ncn+ncn+ncn+jcm`, `ncn+ncn+ncn+jco`, `ncn+ncn+ncn+jcs`, `ncn+ncn+ncn+jct+jxt`, `ncn+ncn+ncn+jp+etn+jxc`, `ncn+ncn+ncn+jxt`, `ncn+ncn+ncn+ncn+jca`, `ncn+ncn+ncn+ncn+jca+jxt`, `ncn+ncn+ncn+ncn+jco`, `ncn+ncn+ncn+xsn+jp+etm`, `ncn+ncn+ncpa`, `ncn+ncn+ncpa+jca`, `ncn+ncn+ncpa+jcm`, `ncn+ncn+ncpa+jco`, `ncn+ncn+ncpa+jcs`, `ncn+ncn+ncpa+jxc`, `ncn+ncn+ncpa+jxt`, `ncn+ncn+ncpa+ncn`, `ncn+ncn+ncpa+ncn+jca`, `ncn+ncn+ncpa+ncn+jcj`, `ncn+ncn+ncpa+ncn+jcm`, `ncn+ncn+ncpa+ncn+jxt`, `ncn+ncn+xsn`, `ncn+ncn+xsn+jca`, `ncn+ncn+xsn+jca+jxt`, `ncn+ncn+xsn+jcj`, `ncn+ncn+xsn+jcm`, `ncn+ncn+xsn+jco`, `ncn+ncn+xsn+jcs`, `ncn+ncn+xsn+jct`, `ncn+ncn+xsn+jp+ecs`, `ncn+ncn+xsn+jp+ep+ef`, `ncn+ncn+xsn+jp+etm`, `ncn+ncn+xsn+jxc`, `ncn+ncn+xsn+jxc+jcs`, `ncn+ncn+xsn+jxt`, `ncn+ncn+xsv+ecc`, `ncn+ncn+xsv+etm`, `ncn+ncpa`, `ncn+ncpa+jca`, `ncn+ncpa+jca+jcm`, `ncn+ncpa+jca+jxc`, `ncn+ncpa+jca+jxt`, `ncn+ncpa+jcc`, `ncn+ncpa+jcj`, `ncn+ncpa+jcm`, `ncn+ncpa+jco`, `ncn+ncpa+jcr`, `ncn+ncpa+jcs`, `ncn+ncpa+jct`, `ncn+ncpa+jct+jcm`, `ncn+ncpa+jct+jxt`, `ncn+ncpa+jp+ecc`, `ncn+ncpa+jp+ecc+jxc`, `ncn+ncpa+jp+ecs`, `ncn+ncpa+jp+ecs+jxc`, `ncn+ncpa+jp+ef`, `ncn+ncpa+jp+ef+jcr`, `ncn+ncpa+jp+ef+jcr+jxc`, `ncn+ncpa+jp+ep+ef`, `ncn+ncpa+jp+ep+etm`, `ncn+ncpa+jp+ep+etn`, `ncn+ncpa+jp+etm`, `ncn+ncpa+jxc`, `ncn+ncpa+jxc+jca+jxc`, `ncn+ncpa+jxc+jco`, `ncn+ncpa+jxc+jcs`, `ncn+ncpa+jxt`, `ncn+ncpa+nbn+jcs`, `ncn+ncpa+ncn`, `ncn+ncpa+ncn+jca`, `ncn+ncpa+ncn+jca+jcm`, `ncn+ncpa+ncn+jca+jxc`, `ncn+ncpa+ncn+jca+jxt`, `ncn+ncpa+ncn+jcj`, `ncn+ncpa+ncn+jcm`, `ncn+ncpa+ncn+jco`, `ncn+ncpa+ncn+jcs`, `ncn+ncpa+ncn+jct`, `ncn+ncpa+ncn+jct+jcm`, `ncn+ncpa+ncn+jp+ef+jcr`, `ncn+ncpa+ncn+jp+ep+etm`, `ncn+ncpa+ncn+jxc`, `ncn+ncpa+ncn+jxt`, `ncn+ncpa+ncn+xsn+jcm`, `ncn+ncpa+ncn+xsn+jxt`, `ncn+ncpa+ncpa`, `ncn+ncpa+ncpa+jca`, `ncn+ncpa+ncpa+jcj`, `ncn+ncpa+ncpa+jcm`, `ncn+ncpa+ncpa+jco`, `ncn+ncpa+ncpa+jcs`, `ncn+ncpa+ncpa+jp+ep+ef`, `ncn+ncpa+ncpa+jxt`, `ncn+ncpa+ncpa+ncn`, `ncn+ncpa+xsn`, `ncn+ncpa+xsn+jcm`, `ncn+ncpa+xsn+jco`, `ncn+ncpa+xsn+jcs`, `ncn+ncpa+xsn+jp+ecc`, `ncn+ncpa+xsn+jp+etm`, `ncn+ncpa+xsn+jxt`, `ncn+ncpa+xsv+ecc`, `ncn+ncpa+xsv+ecs`, `ncn+ncpa+xsv+ecx`, `ncn+ncpa+xsv+ecx+px+etm`, `ncn+ncpa+xsv+ef`, `ncn+ncpa+xsv+ef+jcm`, `ncn+ncpa+xsv+ef+jcr`, `ncn+ncpa+xsv+etm`, `ncn+ncpa+xsv+etn`, _(truncated: full list in pipeline meta)_ |
-| **`morphologizer`** | `POS=CCONJ`, `POS=ADV`, `POS=SCONJ`, `POS=DET`, `POS=NOUN`, `POS=VERB`, `POS=ADJ`, `POS=PUNCT`, `POS=AUX`, `POS=PRON`, `POS=PROPN`, `POS=NUM`, `POS=INTJ`, `POS=PART`, `POS=X`, `POS=ADP`, `POS=SYM` |
+| **`tagger`** | `_SP`, `ecs`, `etm`, `f`, `f+f+jcj`, `f+f+jcs`, `f+f+jct`, `f+f+jxt`, `f+jca`, `f+jca+jp+ecc`, `f+jca+jp+ep+ef`, `f+jca+jxc`, `f+jca+jxc+jcm`, `f+jca+jxt`, `f+jcj`, `f+jcm`, `f+jco`, `f+jcs`, `f+jct`, `f+jct+jcm`, `f+jp+ef`, `f+jp+ep+ef`, `f+jp+etm`, `f+jxc`, `f+jxt`, `f+ncn`, `f+ncn+jcm`, `f+ncn+jcs`, `f+ncn+jp+ecc`, `f+ncn+jxt`, `f+ncpa+jcm`, `f+npp+jcs`, `f+nq`, `f+xsn`, `f+xsn+jco`, `f+xsn+jxt`, `ii`, `jca`, `jca+jcm`, `jca+jxc`, `jca+jxt`, `jcc`, `jcj`, `jcm`, `jco`, `jcr`, `jcr+jxc`, `jcs`, `jct`, `jct+jcm`, `jct+jxt`, `jp+ecc`, `jp+ecs`, `jp+ef`, `jp+ef+jcr`, `jp+ef+jcr+jxc`, `jp+ep+ecs`, `jp+ep+ef`, `jp+ep+etm`, `jp+ep+etn`, `jp+etm`, `jp+etn`, `jp+etn+jco`, `jp+etn+jxc`, `jxc`, `jxc+jca`, `jxc+jco`, `jxc+jcs`, `jxt`, `mad`, `mad+jxc`, `mad+jxt`, `mag`, `mag+jca`, `mag+jcm`, `mag+jcs`, `mag+jp+ef+jcr`, `mag+jxc`, `mag+jxc+jxc`, `mag+jxt`, `mag+xsn`, `maj`, `maj+jxc`, `maj+jxt`, `mma`, `mmd`, `nbn`, `nbn+jca`, `nbn+jca+jcj`, `nbn+jca+jcm`, `nbn+jca+jp+ef`, `nbn+jca+jxc`, `nbn+jca+jxt`, `nbn+jcc`, `nbn+jcj`, `nbn+jcm`, `nbn+jco`, `nbn+jcr`, `nbn+jcs`, `nbn+jct`, `nbn+jct+jcm`, `nbn+jct+jxt`, `nbn+jp+ecc`, `nbn+jp+ecs`, `nbn+jp+ecs+jca`, `nbn+jp+ecs+jcm`, `nbn+jp+ecs+jco`, `nbn+jp+ecs+jxc`, `nbn+jp+ecs+jxt`, `nbn+jp+ecx`, `nbn+jp+ef`, `nbn+jp+ef+jca`, `nbn+jp+ef+jco`, `nbn+jp+ef+jcr`, `nbn+jp+ef+jcr+jxc`, `nbn+jp+ef+jcr+jxt`, `nbn+jp+ef+jcs`, `nbn+jp+ef+jxc`, `nbn+jp+ef+jxc+jco`, `nbn+jp+ef+jxf`, `nbn+jp+ef+jxt`, `nbn+jp+ep+ecc`, `nbn+jp+ep+ecs`, `nbn+jp+ep+ecs+jxc`, `nbn+jp+ep+ef`, `nbn+jp+ep+ef+jcr`, `nbn+jp+ep+etm`, `nbn+jp+ep+etn`, `nbn+jp+ep+etn+jco`, `nbn+jp+ep+etn+jcs`, `nbn+jp+etm`, `nbn+jp+etn`, `nbn+jp+etn+jca`, `nbn+jp+etn+jca+jxt`, `nbn+jp+etn+jco`, `nbn+jp+etn+jcs`, `nbn+jp+etn+jxc`, `nbn+jp+etn+jxt`, `nbn+jxc`, `nbn+jxc+jca`, `nbn+jxc+jca+jxc`, `nbn+jxc+jca+jxt`, `nbn+jxc+jcc`, `nbn+jxc+jcm`, `nbn+jxc+jco`, `nbn+jxc+jcs`, `nbn+jxc+jp+ef`, `nbn+jxc+jxc`, `nbn+jxc+jxt`, `nbn+jxt`, `nbn+nbn`, `nbn+nbn+jp+ef`, `nbn+xsm+ecs`, `nbn+xsm+ef`, `nbn+xsm+ep+ef`, `nbn+xsm+ep+ef+jcr`, `nbn+xsm+etm`, `nbn+xsn`, `nbn+xsn+jca`, `nbn+xsn+jca+jp+ef+jcr`, `nbn+xsn+jca+jxc`, `nbn+xsn+jca+jxt`, `nbn+xsn+jcm`, `nbn+xsn+jco`, `nbn+xsn+jcs`, `nbn+xsn+jct`, `nbn+xsn+jp+ecc`, `nbn+xsn+jp+ecs`, `nbn+xsn+jp+ef`, `nbn+xsn+jp+ef+jcr`, `nbn+xsn+jp+ep+ef`, `nbn+xsn+jxc`, `nbn+xsn+jxt`, `nbn+xsv+etm`, `nbu`, `nbu+jca`, `nbu+jca+jxc`, `nbu+jca+jxt`, `nbu+jcc`, `nbu+jcc+jxc`, `nbu+jcj`, `nbu+jcm`, `nbu+jco`, `nbu+jcs`, `nbu+jct`, `nbu+jct+jxc`, `nbu+jp+ecc`, `nbu+jp+ecs`, `nbu+jp+ef`, `nbu+jp+ef+jcr`, `nbu+jp+ef+jxc`, `nbu+jp+ep+ecc`, `nbu+jp+ep+ecs`, `nbu+jp+ep+ef`, `nbu+jp+ep+ef+jcr`, `nbu+jp+ep+etm`, `nbu+jp+ep+etn+jco`, `nbu+jp+etm`, `nbu+jxc`, `nbu+jxc+jca`, `nbu+jxc+jcs`, `nbu+jxc+jp+ef`, `nbu+jxc+jp+ep+ef`, `nbu+jxc+jxt`, `nbu+jxt`, `nbu+ncn`, `nbu+ncn+jca`, `nbu+ncn+jcm`, `nbu+xsn`, `nbu+xsn+jca`, `nbu+xsn+jca+jxc`, `nbu+xsn+jca+jxt`, `nbu+xsn+jcm`, `nbu+xsn+jco`, `nbu+xsn+jcs`, `nbu+xsn+jp+ecs`, `nbu+xsn+jp+ep+ef`, `nbu+xsn+jxc`, `nbu+xsn+jxc+jxt`, `nbu+xsn+jxt`, `nbu+xsv+ecc`, `nbu+xsv+etm`, `ncn`, `ncn+f+ncpa+jco`, `ncn+jca`, `ncn+jca+jca`, `ncn+jca+jcc`, `ncn+jca+jcj`, `ncn+jca+jcm`, `ncn+jca+jcs`, `ncn+jca+jct`, `ncn+jca+jp+ecc`, `ncn+jca+jp+ecs`, `ncn+jca+jp+ef`, `ncn+jca+jp+ep+ef`, `ncn+jca+jp+etm`, `ncn+jca+jp+etn+jxt`, `ncn+jca+jxc`, `ncn+jca+jxc+jcc`, `ncn+jca+jxc+jcm`, `ncn+jca+jxc+jxc`, `ncn+jca+jxc+jxt`, `ncn+jca+jxt`, `ncn+jcc`, `ncn+jcc+jxc`, `ncn+jcj`, `ncn+jcj+jxt`, `ncn+jcm`, `ncn+jco`, `ncn+jcr`, `ncn+jcr+jxc`, `ncn+jcs`, `ncn+jcs+jxt`, `ncn+jct`, `ncn+jct+jcm`, `ncn+jct+jxc`, `ncn+jct+jxt`, `ncn+jcv`, `ncn+jp+ecc`, `ncn+jp+ecc+jct`, `ncn+jp+ecc+jxc`, `ncn+jp+ecs`, `ncn+jp+ecs+jcm`, `ncn+jp+ecs+jco`, `ncn+jp+ecs+jxc`, `ncn+jp+ecs+jxt`, `ncn+jp+ecx`, `ncn+jp+ef`, `ncn+jp+ef+jca`, `ncn+jp+ef+jcm`, `ncn+jp+ef+jco`, `ncn+jp+ef+jcr`, `ncn+jp+ef+jcr+jxc`, `ncn+jp+ef+jcr+jxt`, `ncn+jp+ef+jp+etm`, `ncn+jp+ef+jxc`, `ncn+jp+ef+jxf`, `ncn+jp+ef+jxt`, `ncn+jp+ep+ecc`, `ncn+jp+ep+ecs`, `ncn+jp+ep+ecs+jxc`, `ncn+jp+ep+ecx`, `ncn+jp+ep+ef`, `ncn+jp+ep+ef+jcr`, `ncn+jp+ep+ef+jcr+jxc`, `ncn+jp+ep+ef+jxc`, `ncn+jp+ep+ef+jxf`, `ncn+jp+ep+ef+jxt`, `ncn+jp+ep+ep+etm`, `ncn+jp+ep+etm`, `ncn+jp+ep+etn`, `ncn+jp+ep+etn+jca`, `ncn+jp+ep+etn+jca+jxc`, `ncn+jp+ep+etn+jco`, `ncn+jp+ep+etn+jcs`, `ncn+jp+ep+etn+jxt`, `ncn+jp+etm`, `ncn+jp+etn`, `ncn+jp+etn+jca`, `ncn+jp+etn+jca+jxc`, `ncn+jp+etn+jca+jxt`, `ncn+jp+etn+jco`, `ncn+jp+etn+jcs`, `ncn+jp+etn+jct`, `ncn+jp+etn+jxc`, `ncn+jp+etn+jxt`, `ncn+jxc`, `ncn+jxc+jca`, `ncn+jxc+jca+jxc`, `ncn+jxc+jca+jxt`, `ncn+jxc+jcc`, `ncn+jxc+jcm`, `ncn+jxc+jco`, `ncn+jxc+jcs`, `ncn+jxc+jct+jxt`, `ncn+jxc+jp+ef`, `ncn+jxc+jp+ef+jcr`, `ncn+jxc+jp+ep+ecs`, `ncn+jxc+jp+ep+ef`, `ncn+jxc+jp+etm`, `ncn+jxc+jxc`, `ncn+jxc+jxt`, `ncn+jxt`, `ncn+jxt+jcm`, `ncn+jxt+jxc`, `ncn+nbn`, `ncn+nbn+jca`, `ncn+nbn+jcm`, `ncn+nbn+jcs`, `ncn+nbn+jp+ecc`, `ncn+nbn+jp+ep+ef`, `ncn+nbn+jxc`, `ncn+nbn+jxt`, `ncn+nbu`, `ncn+nbu+jca`, `ncn+nbu+jcm`, `ncn+nbu+jco`, `ncn+nbu+jp+ef`, `ncn+nbu+jxc`, `ncn+nbu+ncn`, `ncn+ncn`, `ncn+ncn+jca`, `ncn+ncn+jca+jcc`, `ncn+ncn+jca+jcm`, `ncn+ncn+jca+jxc`, `ncn+ncn+jca+jxc+jcm`, `ncn+ncn+jca+jxc+jxc`, `ncn+ncn+jca+jxt`, `ncn+ncn+jcc`, `ncn+ncn+jcj`, `ncn+ncn+jcm`, `ncn+ncn+jco`, `ncn+ncn+jcr`, `ncn+ncn+jcs`, `ncn+ncn+jct`, `ncn+ncn+jct+jcm`, `ncn+ncn+jct+jxc`, `ncn+ncn+jct+jxt`, `ncn+ncn+jp+ecc`, `ncn+ncn+jp+ecs`, `ncn+ncn+jp+ef`, `ncn+ncn+jp+ef+jcm`, `ncn+ncn+jp+ef+jcr`, `ncn+ncn+jp+ef+jcs`, `ncn+ncn+jp+ep+ecc`, `ncn+ncn+jp+ep+ecs`, `ncn+ncn+jp+ep+ef`, `ncn+ncn+jp+ep+ef+jcr`, `ncn+ncn+jp+ep+ep+etm`, `ncn+ncn+jp+ep+etm`, `ncn+ncn+jp+ep+etn`, `ncn+ncn+jp+etm`, `ncn+ncn+jp+etn`, `ncn+ncn+jp+etn+jca`, `ncn+ncn+jp+etn+jco`, `ncn+ncn+jp+etn+jxc`, `ncn+ncn+jxc`, `ncn+ncn+jxc+jca`, `ncn+ncn+jxc+jcc`, `ncn+ncn+jxc+jcm`, `ncn+ncn+jxc+jco`, `ncn+ncn+jxc+jcs`, `ncn+ncn+jxc+jxc`, `ncn+ncn+jxt`, `ncn+ncn+nbn`, `ncn+ncn+ncn`, `ncn+ncn+ncn+jca`, `ncn+ncn+ncn+jca+jcm`, `ncn+ncn+ncn+jca+jxt`, `ncn+ncn+ncn+jcj`, `ncn+ncn+ncn+jcm`, `ncn+ncn+ncn+jco`, `ncn+ncn+ncn+jcs`, `ncn+ncn+ncn+jct+jxt`, `ncn+ncn+ncn+jp+etn+jxc`, `ncn+ncn+ncn+jxt`, `ncn+ncn+ncn+ncn+jca`, `ncn+ncn+ncn+ncn+jca+jxt`, `ncn+ncn+ncn+ncn+jco`, `ncn+ncn+ncn+xsn+jp+etm`, `ncn+ncn+ncpa`, `ncn+ncn+ncpa+jca`, `ncn+ncn+ncpa+jcm`, `ncn+ncn+ncpa+jco`, `ncn+ncn+ncpa+jcs`, `ncn+ncn+ncpa+jxc`, `ncn+ncn+ncpa+jxt`, `ncn+ncn+ncpa+ncn`, `ncn+ncn+ncpa+ncn+jca`, `ncn+ncn+ncpa+ncn+jcj`, `ncn+ncn+ncpa+ncn+jcm`, `ncn+ncn+ncpa+ncn+jxt`, `ncn+ncn+xsn`, `ncn+ncn+xsn+jca`, `ncn+ncn+xsn+jca+jxt`, `ncn+ncn+xsn+jcj`, `ncn+ncn+xsn+jcm`, `ncn+ncn+xsn+jco`, `ncn+ncn+xsn+jcs`, `ncn+ncn+xsn+jct`, `ncn+ncn+xsn+jp+ecs`, `ncn+ncn+xsn+jp+ep+ef`, `ncn+ncn+xsn+jp+etm`, `ncn+ncn+xsn+jxc`, `ncn+ncn+xsn+jxc+jcs`, `ncn+ncn+xsn+jxt`, `ncn+ncn+xsv+ecc`, `ncn+ncn+xsv+etm`, `ncn+ncpa`, `ncn+ncpa+jca`, `ncn+ncpa+jca+jcm`, `ncn+ncpa+jca+jxc`, `ncn+ncpa+jca+jxt`, `ncn+ncpa+jcc`, `ncn+ncpa+jcj`, `ncn+ncpa+jcm`, `ncn+ncpa+jco`, `ncn+ncpa+jcr`, `ncn+ncpa+jcs`, `ncn+ncpa+jct`, `ncn+ncpa+jct+jcm`, `ncn+ncpa+jct+jxt`, `ncn+ncpa+jp+ecc`, `ncn+ncpa+jp+ecc+jxc`, `ncn+ncpa+jp+ecs`, `ncn+ncpa+jp+ecs+jxc`, `ncn+ncpa+jp+ef`, `ncn+ncpa+jp+ef+jcr`, `ncn+ncpa+jp+ef+jcr+jxc`, `ncn+ncpa+jp+ep+ef`, `ncn+ncpa+jp+ep+etm`, `ncn+ncpa+jp+ep+etn`, `ncn+ncpa+jp+etm`, `ncn+ncpa+jxc`, `ncn+ncpa+jxc+jca+jxc`, `ncn+ncpa+jxc+jco`, `ncn+ncpa+jxc+jcs`, `ncn+ncpa+jxt`, `ncn+ncpa+nbn+jcs`, `ncn+ncpa+ncn`, `ncn+ncpa+ncn+jca`, `ncn+ncpa+ncn+jca+jcm`, `ncn+ncpa+ncn+jca+jxc`, `ncn+ncpa+ncn+jca+jxt`, `ncn+ncpa+ncn+jcj`, `ncn+ncpa+ncn+jcm`, `ncn+ncpa+ncn+jco`, `ncn+ncpa+ncn+jcs`, `ncn+ncpa+ncn+jct`, `ncn+ncpa+ncn+jct+jcm`, `ncn+ncpa+ncn+jp+ef+jcr`, `ncn+ncpa+ncn+jp+ep+etm`, `ncn+ncpa+ncn+jxc`, `ncn+ncpa+ncn+jxt`, `ncn+ncpa+ncn+xsn+jcm`, `ncn+ncpa+ncn+xsn+jxt`, `ncn+ncpa+ncpa`, `ncn+ncpa+ncpa+jca`, `ncn+ncpa+ncpa+jcj`, `ncn+ncpa+ncpa+jcm`, `ncn+ncpa+ncpa+jco`, `ncn+ncpa+ncpa+jcs`, `ncn+ncpa+ncpa+jp+ep+ef`, `ncn+ncpa+ncpa+jxt`, `ncn+ncpa+ncpa+ncn`, `ncn+ncpa+xsn`, `ncn+ncpa+xsn+jcm`, `ncn+ncpa+xsn+jco`, `ncn+ncpa+xsn+jcs`, `ncn+ncpa+xsn+jp+ecc`, `ncn+ncpa+xsn+jp+etm`, `ncn+ncpa+xsn+jxt`, `ncn+ncpa+xsv+ecc`, `ncn+ncpa+xsv+ecs`, `ncn+ncpa+xsv+ecx`, `ncn+ncpa+xsv+ecx+px+etm`, `ncn+ncpa+xsv+ef`, `ncn+ncpa+xsv+ef+jcm`, `ncn+ncpa+xsv+ef+jcr`, `ncn+ncpa+xsv+etm`, _(truncated: full list in pipeline meta)_ |
+| **`morphologizer`** | `POS=CCONJ`, `POS=ADV`, `POS=SCONJ`, `POS=DET`, `POS=NOUN`, `POS=VERB`, `POS=ADJ`, `POS=PUNCT`, `POS=SPACE`, `POS=AUX`, `POS=PRON`, `POS=PROPN`, `POS=NUM`, `POS=INTJ`, `POS=PART`, `POS=X`, `POS=ADP`, `POS=SYM` |
 | **`parser`** | `ROOT`, `acl`, `advcl`, `advmod`, `amod`, `appos`, `aux`, `case`, `cc`, `ccomp`, `compound`, `conj`, `cop`, `csubj`, `dep`, `det`, `dislocated`, `fixed`, `flat`, `iobj`, `mark`, `nmod`, `nsubj`, `nummod`, `obj`, `obl`, `punct`, `xcomp` |
 | **`ner`** | `DT`, `LC`, `OG`, `PS`, `QT`, `TI` |
 
@@ -103,14 +103,14 @@ Korean pipeline optimized for CPU. Components: tok2vec, tagger, morphologizer, p
 | `TOKEN_P` | 100.00 |
 | `TOKEN_R` | 100.00 |
 | `TOKEN_F` | 100.00 |
-| `TAG_ACC` | 73.36 |
-| `POS_ACC` | 86.09 |
+| `TAG_ACC` | 73.21 |
+| `POS_ACC` | 86.00 |
 | `SENTS_P` | 100.00 |
 | `SENTS_R` | 100.00 |
 | `SENTS_F` | 100.00 |
-| `DEP_UAS` | 73.76 |
-| `DEP_LAS` | 65.56 |
-| `LEMMA_ACC` | 83.18 |
-| `ENTS_P` | 77.14 |
-| `ENTS_R` | 66.28 |
-| `ENTS_F` | 71.30 |
+| `DEP_UAS` | 74.20 |
+| `DEP_LAS` | 66.15 |
+| `LEMMA_ACC` | 83.40 |
+| `ENTS_P` | 77.02 |
+| `ENTS_R` | 66.47 |
+| `ENTS_F` | 71.36 |

accuracy.json

@@ -3,118 +3,113 @@
   "token_p": 1.0,
   "token_r": 1.0,
   "token_f": 1.0,
-  "tag_acc": 0.7335983702,
-  "pos_acc": 0.8608501296,
+  "tag_acc": 0.7320951759,
+  "pos_acc": 0.860041932,
   "sents_p": 1.0,
   "sents_r": 1.0,
   "sents_f": 1.0,
-  "dep_uas": 0.7375785393,
-  "dep_las": 0.6555857582,
+  "dep_uas": 0.7420346687,
+  "dep_las": 0.6614531114,
   "dep_las_per_type": {
     "amod": {
-      "p": 0.7562056738,
-      "r": 0.7469352014,
-      "f": 0.7515418502
+      "p": 0.7620320856,
+      "r": 0.7486865149,
+      "f": 0.7553003534
     },
     "dislocated": {
-      "p": 0.5577299413,
-      "r": 0.555916775,
-      "f": 0.5568218821
+      "p": 0.561827957,
+      "r": 0.5435630689,
+      "f": 0.5525446134
     },
     "root": {
-      "p": 0.8025169409,
-      "r": 0.8025169409,
-      "f": 0.8025169409
+      "p": 0.8146176186,
+      "r": 0.8146176186,
+      "f": 0.8146176186
     },
     "nmod": {
-      "p": 0.6305841924,
-      "r": 0.6534124629,
-      "f": 0.6417953949
+      "p": 0.626799557,
+      "r": 0.671810089,
+      "f": 0.648524778
     },
     "nsubj": {
-      "p": 0.5475830816,
-      "r": 0.5781499203,
-      "f": 0.5624515128
+      "p": 0.5777604977,
+      "r": 0.5925039872,
+      "f": 0.5850393701
     },
     "advmod": {
-      "p": 0.641955836,
-      "r": 0.6389324961,
-      "f": 0.640440598
+      "p": 0.6664056382,
+      "r": 0.6679748823,
+      "f": 0.6671893375
     },
     "dep": {
-      "p": 0.4827586207,
-      "r": 0.3867403315,
-      "f": 0.4294478528
+      "p": 0.5165562914,
+      "r": 0.4309392265,
+      "f": 0.4698795181
     },
     "conj": {
-      "p": 0.4474660074,
-      "r": 0.4641025641,
-      "f": 0.4556324733
+      "p": 0.4520123839,
+      "r": 0.4679487179,
+      "f": 0.4598425197
     },
     "xcomp": {
-      "p": 0.5263157895,
-      "r": 0.4810996564,
-      "f": 0.5026929982
+      "p": 0.5681818182,
+      "r": 0.5154639175,
+      "f": 0.5405405405
     },
     "flat": {
-      "p": 0.2916666667,
-      "r": 0.0654205607,
-      "f": 0.106870229
+      "p": 0.7142857143,
+      "r": 0.0934579439,
+      "f": 0.1652892562
     },
     "obj": {
-      "p": 0.7117552335,
-      "r": 0.7125201505,
-      "f": 0.7121374866
+      "p": 0.6926293779,
+      "r": 0.7119828049,
+      "f": 0.702172761
     },
     "acl": {
-      "p": 0.6658566221,
-      "r": 0.6574685063,
-      "f": 0.6616359795
+      "p": 0.6581818182,
+      "r": 0.6514697061,
+      "f": 0.654808562
     },
     "advcl": {
-      "p": 0.5574112735,
-      "r": 0.5437881874,
-      "f": 0.5505154639
+      "p": 0.5576005453,
+      "r": 0.55532926,
+      "f": 0.556462585
     },
     "det": {
-      "p": 0.7582781457,
-      "r": 0.8609022556,
-      "f": 0.8063380282
+      "p": 0.7516339869,
+      "r": 0.8646616541,
+      "f": 0.8041958042
     },
     "compound": {
-      "p": 0.6999360205,
-      "r": 0.6678876679,
-      "f": 0.6835363949
+      "p": 0.6823679185,
+      "r": 0.6544566545,
+      "f": 0.6681209099
     },
     "ccomp": {
-      "p": 0.4908946952,
-      "r": 0.5145228216,
-      "f": 0.5024311183
+      "p": 0.5081833061,
+      "r": 0.5153526971,
+      "f": 0.5117428925
     },
     "obl": {
-      "p": 0.6481223922,
-      "r": 0.6357435198,
-      "f": 0.6418732782
+      "p": 0.6657381616,
+      "r": 0.6521145975,
+      "f": 0.6588559614
     },
     "aux": {
-      "p": 0.8774811773,
-      "r": 0.8990182328,
-      "f": 0.8881191548
+      "p": 0.8905817175,
+      "r": 0.9018232819,
+      "f": 0.8961672474
     },
     "cc": {
-      "p": 0.7802547771,
-      "r": 0.8112582781,
-      "f": 0.7954545455
+      "p": 0.807073955,
+      "r": 0.8311258278,
+      "f": 0.8189233279
     },
     "nummod": {
-      "p": 0.8333333333,
-      "r": 0.8115183246,
-      "f": 0.8222811671
-    },
-    "iobj": {
-      "p": 0.7230769231,
-      "r": 0.661971831,
-      "f": 0.6911764706
+      "p": 0.875,
+      "r": 0.8429319372,
+      "f": 0.8586666667
     },
     "discourse": {
       "p": 0.0,
@@ -122,76 +117,81 @@
       "f": 0.0
     },
     "fixed": {
-      "p": 0.9484126984,
-      "r": 1.0,
-      "f": 0.9735234216
+      "p": 0.9596774194,
+      "r": 0.9958158996,
+      "f": 0.977412731
     },
     "csubj": {
-      "p": 0.5157894737,
-      "r": 0.4454545455,
-      "f": 0.4780487805
+      "p": 0.5471698113,
+      "r": 0.5272727273,
+      "f": 0.537037037
     },
     "mark": {
-      "p": 0.6862745098,
-      "r": 0.5384615385,
-      "f": 0.6034482759
+      "p": 0.6666666667,
+      "r": 0.5538461538,
+      "f": 0.6050420168
+    },
+    "iobj": {
+      "p": 0.6666666667,
+      "r": 0.5070422535,
+      "f": 0.576
     },
     "case": {
-      "p": 0.8787878788,
+      "p": 0.8529411765,
       "r": 0.8529411765,
-      "f": 0.8656716418
-    },
-    "appos": {
-      "p": 0.6111111111,
-      "r": 0.7857142857,
-      "f": 0.6875
+      "f": 0.8529411765
     },
     "cop": {
-      "p": 0.75,
-      "r": 0.8,
-      "f": 0.7741935484
+      "p": 0.7647058824,
+      "r": 0.8666666667,
+      "f": 0.8125
     },
     "vocative": {
       "p": 0.0,
       "r": 0.0,
       "f": 0.0
+    },
+    "appos": {
+      "p": 0.6428571429,
+      "r": 0.6428571429,
+      "f": 0.6428571429
     }
   },
-  "lemma_acc": 0.8317806919,
-  "speed": 10661.1584237889,
-  "ents_p": 0.7714191745,
-  "ents_r": 0.6628046627,
-  "ents_f": 0.712999202,
+  "lemma_acc": 0.8340354833,
+  "speed": 12550.4676822577,
+  "ents_p": 0.7701563395,
+  "ents_r": 0.6647121159,
+  "ents_f": 0.7135598362,
   "ents_per_type": {
     "OG": {
-      "p": 0.6825588413,
-      "r": 0.5243393602,
-      "f": 0.5930781332
+      "p": 0.6808894231,
+      "r": 0.5252665739,
+      "f": 0.5930384716
     },
     "PS": {
-      "p": 0.7701958384,
-      "r": 0.5719154738,
-      "f": 0.656408919
+      "p": 0.7770642202,
+      "r": 0.5773687798,
+      "f": 0.6624951115
     },
     "QT": {
-      "p": 0.853619981,
-      "r": 0.8656620712,
-      "f": 0.8595988539
+      "p": 0.8434484905,
+      "r": 0.868868227,
+      "f": 0.8559696778
     },
     "LC": {
-      "p": 0.5845942228,
-      "r": 0.5227552276,
-      "f": 0.5519480519
+      "p": 0.5856847901,
+      "r": 0.5233702337,
+      "f": 0.5527768756
     },
     "DT": {
-      "p": 0.8222118525,
-      "r": 0.7637624621,
-      "f": 0.7919101124
+      "p": 0.8166589111,
+      "r": 0.7607282185,
+      "f": 0.7877019749
     },
     "TI": {
-      "p": 0.8846960168,
-      "r": 0.7743119266,
-      "f": 0.8258317025
+      "p": 0.8952991453,
+      "r": 0.7688073394,
+      "f": 0.8272458045
     }
   }
 }

ko_core_news_sm-any-py3-none-any.whl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:834bd49736cb201f1db9938588235ebe9d938da4f6f27a1c0f88ddbbba981a1d
-size 14706695
+oid sha256:1953f5d7937d3e913d371d432c36f3c9b6c5ea00e219b37b9f7f7e77f10d79e9
+size 14703805

lemmatizer/cfg

@@ -903,250 +903,243 @@
     1708,
     1709,
     1711,
-    1713,
+    1714,
     1716,
-    1718,
-    1721,
-    1722,
-    1725,
-    1728,
+    1719,
+    1720,
+    1723,
+    1726,
+    1727,
     1729,
+    1730,
     1731,
-    1732,
-    1733,
-    1736,
+    1734,
+    1737,
     1739,
-    1741,
+    1742,
     1744,
     1746,
-    1748,
-    1751,
+    1749,
+    1752,
     1754,
-    1756,
-    1761,
+    1759,
+    1762,
     1764,
-    1766,
+    1767,
     1769,
     1771,
     1773,
-    1775,
     120,
-    1777,
+    1775,
+    1776,
     1778,
-    1780,
+    1781,
     1783,
-    1785,
+    1784,
     1786,
     1788,
+    1789,
     1790,
-    1791,
     1792,
     1794,
     1796,
     1798,
-    1800,
+    1801,
     1803,
-    1805,
+    1804,
     1806,
-    1808,
-    1811,
+    1809,
+    1810,
     1812,
-    1814,
     888,
+    1814,
+    1815,
     1816,
     1817,
-    1818,
-    1819,
-    1822,
-    1825,
-    1828,
+    1820,
+    1823,
+    1826,
     1700,
-    1830,
-    1833,
-    1834,
-    1837,
+    1828,
+    1831,
+    1832,
+    1835,
+    1838,
     1840,
-    1842,
-    1845,
+    1843,
+    1846,
     1848,
     1850,
-    1853,
+    1852,
     1855,
+    1856,
     1857,
-    1860,
-    1861,
+    1859,
     1862,
-    1863,
+    1864,
     1865,
     1867,
-    1868,
+    1869,
     1870,
     1872,
-    1873,
-    1875,
-    1877,
-    1879,
+    1874,
+    1876,
+    1878,
     1881,
-    1884,
+    1882,
     1885,
-    1888,
+    1886,
     1889,
-    1892,
-    1894,
+    1891,
+    1895,
+    1897,
     1898,
     1900,
-    1901,
-    1903,
-    1905,
+    1902,
+    1904,
     1907,
+    1908,
     1910,
-    1911,
+    1912,
     1913,
-    1915,
-    1916,
+    1917,
+    1919,
     1920,
-    1922,
     1923,
+    1925,
     1926,
     1928,
     1929,
-    1931,
     1932,
-    1935,
+    1933,
     1936,
-    1939,
+    1938,
     1941,
-    1944,
-    1946,
-    1948,
+    1943,
+    1945,
+    1947,
     1950,
-    1953,
+    1952,
+    1954,
     1955,
-    1957,
+    1956,
     1958,
-    1959,
     1961,
+    1963,
     1964,
-    1966,
     1967,
+    1968,
     1970,
     1971,
     1973,
-    1974,
-    1976,
-    1980,
-    1981,
+    1977,
+    1978,
+    1979,
     1982,
-    1985,
-    1987,
-    1989,
-    1991,
-    1993,
-    1995,
+    1984,
+    1986,
+    1988,
+    1990,
+    1992,
     109,
-    1997,
+    1994,
+    1996,
     1999,
+    2001,
     2002,
     2004,
-    2005,
     2007,
-    2010,
+    2008,
+    2009,
     2011,
-    2012,
-    2014,
-    2016,
+    2013,
+    2015,
     2018,
+    2020,
     2021,
-    2023,
+    2022,
     2024,
-    2025,
     2027,
-    2030,
-    2031,
+    2028,
+    2032,
+    2033,
     2035,
-    2036,
     2038,
+    2039,
     2041,
     2042,
-    2044,
     2045,
+    2046,
     2048,
     2049,
     2051,
-    2052,
-    2054,
+    2053,
+    2055,
     2056,
     2058,
-    2059,
-    2061,
-    2063,
-    2065,
+    2060,
+    2062,
+    2064,
+    2066,
     2067,
     2069,
-    2070,
-    2072,
+    2071,
     2074,
-    2077,
+    2076,
     2079,
-    2081,
-    2084,
-    2085,
-    2088,
+    2080,
+    2083,
     911,
+    2084,
+    2087,
     2089,
-    2092,
+    2091,
+    2093,
     2094,
-    2096,
-    2098,
-    2099,
-    2102,
-    2105,
-    2109,
-    2113,
-    2115,
+    2097,
+    2100,
+    2104,
+    2108,
+    2110,
+    2112,
+    2114,
     2117,
-    2119,
-    2122,
-    2125,
+    2120,
+    2121,
+    2123,
     2126,
-    2128,
-    2131,
+    2127,
+    2130,
     2132,
     2133,
-    2136,
-    2138,
+    2134,
+    2135,
+    2137,
+    611,
     2139,
     2140,
-    2141,
     2143,
-    611,
     2145,
-    2146,
+    2147,
     2149,
     2151,
     2153,
-    2155,
+    2156,
     2157,
+    2158,
     2159,
-    2161,
+    2163,
     2164,
-    2165,
-    2166,
     2167,
-    2171,
+    2170,
     2172,
     2175,
     2178,
     2180,
+    2182,
     2183,
+    2185,
     2186,
-    2188,
-    2190,
-    2191,
-    2193,
-    2194,
-    2196,
-    2197,
-    2199
+    2188
   ]
 }

lemmatizer/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57cc44fd82385dc4acb07594f2430e3f8e96b5a109ff549a83b8e3a338886f96
-size 445866
+oid sha256:e5ca0aee4b1a4d59e98dcd4bc616cd205265ad8e26716e22c4cac3d799a06024
+size 443150

meta.json

@@ -1,14 +1,14 @@
 {
   "lang":"ko",
   "name":"core_news_sm",
-  "version":"3.3.0",
+  "version":"3.4.0",
   "description":"Korean pipeline optimized for CPU. Components: tok2vec, tagger, morphologizer, parser, lemmatizer (trainable_lemmatizer), senter, ner.",
   "author":"Explosion",
   "email":"contact@explosion.ai",
   "url":"https://explosion.ai",
   "license":"CC BY-SA 4.0",
-  "spacy_version":">=3.3.0.dev0,<3.4.0",
-  "spacy_git_version":"849bef2de",
+  "spacy_version":">=3.4.0,<3.5.0",
+  "spacy_git_version":"dd038b536",
   "vectors":{
     "width":0,
     "vectors":0,
@@ -20,6 +20,7 @@
 
     ],
     "tagger":[
+      "_SP",
       "ecs",
       "etm",
       "f",
@@ -2005,6 +2006,7 @@
       "POS=VERB",
       "POS=ADJ",
       "POS=PUNCT",
+      "POS=SPACE",
       "POS=AUX",
       "POS=PRON",
       "POS=PROPN",
@@ -2084,118 +2086,113 @@
     "token_p":1.0,
     "token_r":1.0,
     "token_f":1.0,
-    "tag_acc":0.7335983702,
-    "pos_acc":0.8608501296,
+    "tag_acc":0.7320951759,
+    "pos_acc":0.860041932,
     "sents_p":1.0,
     "sents_r":1.0,
     "sents_f":1.0,
-    "dep_uas":0.7375785393,
-    "dep_las":0.6555857582,
+    "dep_uas":0.7420346687,
+    "dep_las":0.6614531114,
     "dep_las_per_type":{
       "amod":{
-        "p":0.7562056738,
-        "r":0.7469352014,
-        "f":0.7515418502
+        "p":0.7620320856,
+        "r":0.7486865149,
+        "f":0.7553003534
       },
       "dislocated":{
-        "p":0.5577299413,
-        "r":0.555916775,
-        "f":0.5568218821
+        "p":0.561827957,
+        "r":0.5435630689,
+        "f":0.5525446134
       },
       "root":{
-        "p":0.8025169409,
-        "r":0.8025169409,
-        "f":0.8025169409
+        "p":0.8146176186,
+        "r":0.8146176186,
+        "f":0.8146176186
       },
       "nmod":{
-        "p":0.6305841924,
-        "r":0.6534124629,
-        "f":0.6417953949
+        "p":0.626799557,
+        "r":0.671810089,
+        "f":0.648524778
       },
       "nsubj":{
-        "p":0.5475830816,
-        "r":0.5781499203,
-        "f":0.5624515128
+        "p":0.5777604977,
+        "r":0.5925039872,
+        "f":0.5850393701
       },
       "advmod":{
-        "p":0.641955836,
-        "r":0.6389324961,
-        "f":0.640440598
+        "p":0.6664056382,
+        "r":0.6679748823,
+        "f":0.6671893375
       },
       "dep":{
-        "p":0.4827586207,
-        "r":0.3867403315,
-        "f":0.4294478528
+        "p":0.5165562914,
+        "r":0.4309392265,
+        "f":0.4698795181
       },
       "conj":{
-        "p":0.4474660074,
-        "r":0.4641025641,
-        "f":0.4556324733
+        "p":0.4520123839,
+        "r":0.4679487179,
+        "f":0.4598425197
       },
       "xcomp":{
-        "p":0.5263157895,
-        "r":0.4810996564,
-        "f":0.5026929982
+        "p":0.5681818182,
+        "r":0.5154639175,
+        "f":0.5405405405
       },
       "flat":{
-        "p":0.2916666667,
-        "r":0.0654205607,
-        "f":0.106870229
+        "p":0.7142857143,
+        "r":0.0934579439,
+        "f":0.1652892562
       },
       "obj":{
-        "p":0.7117552335,
-        "r":0.7125201505,
-        "f":0.7121374866
+        "p":0.6926293779,
+        "r":0.7119828049,
+        "f":0.702172761
       },
       "acl":{
-        "p":0.6658566221,
-        "r":0.6574685063,
-        "f":0.6616359795
+        "p":0.6581818182,
+        "r":0.6514697061,
+        "f":0.654808562
       },
       "advcl":{
-        "p":0.5574112735,
-        "r":0.5437881874,
-        "f":0.5505154639
+        "p":0.5576005453,
+        "r":0.55532926,
+        "f":0.556462585
       },
       "det":{
-        "p":0.7582781457,
-        "r":0.8609022556,
-        "f":0.8063380282
+        "p":0.7516339869,
+        "r":0.8646616541,
+        "f":0.8041958042
       },
       "compound":{
-        "p":0.6999360205,
-        "r":0.6678876679,
-        "f":0.6835363949
+        "p":0.6823679185,
+        "r":0.6544566545,
+        "f":0.6681209099
       },
       "ccomp":{
-        "p":0.4908946952,
-        "r":0.5145228216,
-        "f":0.5024311183
+        "p":0.5081833061,
+        "r":0.5153526971,
+        "f":0.5117428925
       },
       "obl":{
-        "p":0.6481223922,
-        "r":0.6357435198,
-        "f":0.6418732782
+        "p":0.6657381616,
+        "r":0.6521145975,
+        "f":0.6588559614
       },
       "aux":{
-        "p":0.8774811773,
-        "r":0.8990182328,
-        "f":0.8881191548
+        "p":0.8905817175,
+        "r":0.9018232819,
+        "f":0.8961672474
       },
       "cc":{
-        "p":0.7802547771,
-        "r":0.8112582781,
-        "f":0.7954545455
+        "p":0.807073955,
+        "r":0.8311258278,
+        "f":0.8189233279
       },
       "nummod":{
-        "p":0.8333333333,
-        "r":0.8115183246,
-        "f":0.8222811671
-      },
-      "iobj":{
-        "p":0.7230769231,
-        "r":0.661971831,
-        "f":0.6911764706
+        "p":0.875,
+        "r":0.8429319372,
+        "f":0.8586666667
       },
       "discourse":{
         "p":0.0,
@@ -2203,76 +2200,81 @@
         "f":0.0
       },
       "fixed":{
-        "p":0.9484126984,
-        "r":1.0,
-        "f":0.9735234216
+        "p":0.9596774194,
+        "r":0.9958158996,
+        "f":0.977412731
       },
       "csubj":{
-        "p":0.5157894737,
-        "r":0.4454545455,
-        "f":0.4780487805
+        "p":0.5471698113,
+        "r":0.5272727273,
+        "f":0.537037037
       },
       "mark":{
-        "p":0.6862745098,
-        "r":0.5384615385,
-        "f":0.6034482759
+        "p":0.6666666667,
+        "r":0.5538461538,
+        "f":0.6050420168
+      },
+      "iobj":{
+        "p":0.6666666667,
+        "r":0.5070422535,
+        "f":0.576
       },
       "case":{
-        "p":0.8787878788,
+        "p":0.8529411765,
         "r":0.8529411765,
-        "f":0.8656716418
-      },
-      "appos":{
-        "p":0.6111111111,
-        "r":0.7857142857,
-        "f":0.6875
+        "f":0.8529411765
       },
       "cop":{
-        "p":0.75,
-        "r":0.8,
-        "f":0.7741935484
+        "p":0.7647058824,
+        "r":0.8666666667,
+        "f":0.8125
       },
       "vocative":{
         "p":0.0,
         "r":0.0,
         "f":0.0
+      },
+      "appos":{
+        "p":0.6428571429,
+        "r":0.6428571429,
+        "f":0.6428571429
       }
     },
-    "lemma_acc":0.8317806919,
-    "speed":10661.1584237889,
-    "ents_p":0.7714191745,
-    "ents_r":0.6628046627,
-    "ents_f":0.712999202,
+    "lemma_acc":0.8340354833,
+    "speed":12550.4676822577,
+    "ents_p":0.7701563395,
+    "ents_r":0.6647121159,
+    "ents_f":0.7135598362,
     "ents_per_type":{
       "OG":{
-        "p":0.6825588413,
-        "r":0.5243393602,
-        "f":0.5930781332
+        "p":0.6808894231,
+        "r":0.5252665739,
+        "f":0.5930384716
       },
       "PS":{
-        "p":0.7701958384,
-        "r":0.5719154738,
-        "f":0.656408919
+        "p":0.7770642202,
+        "r":0.5773687798,
+        "f":0.6624951115
       },
       "QT":{
-        "p":0.853619981,
-        "r":0.8656620712,
-        "f":0.8595988539
+        "p":0.8434484905,
+        "r":0.868868227,
+        "f":0.8559696778
       },
       "LC":{
-        "p":0.5845942228,
-        "r":0.5227552276,
-        "f":0.5519480519
+        "p":0.5856847901,
+        "r":0.5233702337,
+        "f":0.5527768756
       },
       "DT":{
-        "p":0.8222118525,
-        "r":0.7637624621,
-        "f":0.7919101124
+        "p":0.8166589111,
+        "r":0.7607282185,
+        "f":0.7877019749
       },
       "TI":{
-        "p":0.8846960168,
-        "r":0.7743119266,
-        "f":0.8258317025
+        "p":0.8952991453,
+        "r":0.7688073394,
+        "f":0.8272458045
       }
     }
   },

morphologizer/cfg

@@ -9,6 +9,7 @@
     "POS=VERB":"",
     "POS=ADJ":"",
     "POS=PUNCT":"",
+    "POS=SPACE":"",
     "POS=AUX":"",
     "POS=PRON":"",
     "POS=PROPN":"",
@@ -28,6 +29,7 @@
     "POS=VERB":100,
     "POS=ADJ":84,
     "POS=PUNCT":97,
+    "POS=SPACE":103,
     "POS=AUX":87,
     "POS=PRON":95,
     "POS=PROPN":96,

morphologizer/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d4dfef2d668edd7aaeb8fbab39adb5925232e1281c0e4dfdb8f8d96d352432a
-size 7025
+oid sha256:c1ce2045adff96e3bdb86778b378d82bd658547eec6ab7ff47576196de360499
+size 7413

ner/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62f5767bee31144379e842d266eee700267837fc3b4486f9704625b21f64ebe1
+oid sha256:904260ca33ed768cf83c513b0d196063e4569321698899eeecdcc8f1cb0f9537
 size 6272282

ner/moves

@@ -1 +1 @@
-��moves�
,{"0":{},"1":{"PS":16127,"QT":13487,"DT":10090,"OG":9793,"LC":8337,"TI":2926},"2":{"PS":16127,"QT":13487,"DT":10090,"OG":9793,"LC":8337,"TI":2926},"3":{"PS":16127,"QT":13487,"DT":10090,"OG":9793,"LC":8337,"TI":2926},"4":{"PS":16127,"QT":13487,"DT":10090,"OG":9793,"LC":8337,"TI":2926,"":1},"5":{"":1}}�cfg��neg_key�
+��moves�
,{"0":{},"1":{"PS":16134,"QT":13491,"DT":10094,"OG":9801,"LC":8341,"TI":2933},"2":{"PS":16134,"QT":13491,"DT":10094,"OG":9801,"LC":8341,"TI":2933},"3":{"PS":16134,"QT":13491,"DT":10094,"OG":9801,"LC":8341,"TI":2933},"4":{"PS":16134,"QT":13491,"DT":10094,"OG":9801,"LC":8341,"TI":2933,"":1},"5":{"":1}}�cfg��neg_key�

parser/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e91d4945fcaea012914bf52396bd9d4ec0a65629041277caf957447e7bc8f629
+oid sha256:462e720a54dc098101de8567256d17cae693686b2140d5b2d3e8ad0d2b1ab132
 size 305088

parser/moves

@@ -1 +1 @@
-��moves��{"0":{"":202496},"1":{"":70942},"2":{"compound":20632,"obj":19819,"nmod":17977,"acl":17852,"advcl":16547,"dislocated":15591,"advmod":15157,"nsubj":14107,"amod":13975,"ccomp":12588,"obl":9740,"det":4235,"cc":3779,"xcomp":3414,"nummod":2654,"dep":2533,"dislocated||conj":2002,"punct":1803,"csubj":1008,"iobj":823,"advmod||conj":769,"ccomp||conj":717,"cc||conj":705,"mark":635,"nmod||conj":606,"advcl||conj":586,"nsubj||conj":521,"acl||conj":425,"obj||conj":287,"amod||conj":278,"compound||conj":184,"xcomp||conj":169,"obl||conj":153,"dep||conj":64,"det||conj":51,"iobj||conj":31},"3":{"punct":31170,"conj":17608,"aux":16034,"fixed":2776,"case":1120,"appos":956,"flat":595,"advmod":311,"cop":268,"dep":0},"4":{"ROOT":23010}}�cfg��neg_key�
+��moves��{"0":{"":202502},"1":{"":72363},"2":{"compound":20632,"obj":19819,"nmod":17977,"acl":17852,"advcl":16547,"dislocated":15591,"advmod":15157,"nsubj":14107,"amod":13975,"ccomp":12588,"obl":9740,"det":4235,"cc":3779,"xcomp":3414,"nummod":2654,"dep":2539,"dislocated||conj":2002,"punct":1803,"csubj":1008,"iobj":823,"advmod||conj":769,"ccomp||conj":717,"cc||conj":705,"mark":635,"nmod||conj":606,"advcl||conj":586,"nsubj||conj":521,"acl||conj":425,"obj||conj":287,"amod||conj":278,"compound||conj":184,"xcomp||conj":169,"obl||conj":153,"dep||conj":64,"det||conj":51,"iobj||conj":31},"3":{"punct":31170,"conj":17608,"aux":16034,"fixed":2776,"dep":1443,"case":1120,"appos":956,"flat":595,"advmod":311,"cop":268},"4":{"ROOT":23010}}�cfg��neg_key�

senter/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6525f344bfbf7236886310578daed1208bb6f99812a57e81458e32aaab85875
+oid sha256:2c3f42c9a0165f02e19a21174df4d1fb4fda8008e61ab09e9485a78c6598f170
 size 197089

tagger/cfg

@@ -1,5 +1,6 @@
 {
   "labels":[
+    "_SP",
     "ecs",
     "etm",
     "f",

tagger/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94c035f00ea44c6c909c3f77aaa9801a70a784af2457d86d3b3d392c2ee7f978
-size 766742
+oid sha256:bb9add975832b2f42c520904a8ef1b8f17fefda77cff5e53f197cbaa744c96cb
+size 767130

tok2vec/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83c5ee1acdaf72dfbb0fc5861a065ba79225ba36aa0170a7b7f00530db11339b
+oid sha256:4c2af6b96552cc0686ca14bfa05aa734924d67a05b905791138ed3fffa8df118
 size 6139229

vocab/strings.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6abded2cba340f092fd47b90dd5d4c640487c814e5ce9d10fe330c0366393429
-size 10114332
+oid sha256:f04ab95fb3a6ca98589705130e870b3bbac7239bb1d3367a3993bccf6f3d5212
+size 10081761