adrianeboyd
commited on
Commit
•
f989ad0
1
Parent(s):
cb7be32
Update spaCy pipeline
Browse files- LICENSES_SOURCES +1 -1
- README.md +26 -26
- accuracy.json +110 -110
- ko_core_news_md-any-py3-none-any.whl +2 -2
- lemmatizer/cfg +126 -133
- lemmatizer/model +2 -2
- lemmatizer/trees +0 -0
- meta.json +116 -114
- morphologizer/cfg +2 -0
- morphologizer/model +2 -2
- ner/model +1 -1
- ner/moves +1 -1
- parser/model +1 -1
- parser/moves +1 -1
- senter/model +1 -1
- tagger/cfg +1 -0
- tagger/model +2 -2
- tok2vec/model +1 -1
- vocab/strings.json +2 -2
LICENSES_SOURCES
CHANGED
@@ -878,7 +878,7 @@ Creative Commons may be contacted at creativecommons.org.
|
|
878 |
|
879 |
|
880 |
|
881 |
-
# Explosion
|
882 |
|
883 |
* Author: Explosion
|
884 |
* URL: https://github.com/explosion/spacy-vectors-builder
|
|
|
878 |
|
879 |
|
880 |
|
881 |
+
# Explosion Vectors (OSCAR 2109 + Wikipedia + OpenSubtitles + WMT News Crawl)
|
882 |
|
883 |
* Author: Explosion
|
884 |
* URL: https://github.com/explosion/spacy-vectors-builder
|
README.md
CHANGED
@@ -14,55 +14,55 @@ model-index:
|
|
14 |
metrics:
|
15 |
- name: NER Precision
|
16 |
type: precision
|
17 |
-
value: 0.
|
18 |
- name: NER Recall
|
19 |
type: recall
|
20 |
-
value: 0.
|
21 |
- name: NER F Score
|
22 |
type: f_score
|
23 |
-
value: 0.
|
24 |
- task:
|
25 |
name: TAG
|
26 |
type: token-classification
|
27 |
metrics:
|
28 |
- name: TAG (XPOS) Accuracy
|
29 |
type: accuracy
|
30 |
-
value: 0.
|
31 |
- task:
|
32 |
name: POS
|
33 |
type: token-classification
|
34 |
metrics:
|
35 |
- name: POS (UPOS) Accuracy
|
36 |
type: accuracy
|
37 |
-
value: 0.
|
38 |
- task:
|
39 |
name: LEMMA
|
40 |
type: token-classification
|
41 |
metrics:
|
42 |
- name: Lemma Accuracy
|
43 |
type: accuracy
|
44 |
-
value: 0.
|
45 |
- task:
|
46 |
name: UNLABELED_DEPENDENCIES
|
47 |
type: token-classification
|
48 |
metrics:
|
49 |
- name: Unlabeled Attachment Score (UAS)
|
50 |
type: f_score
|
51 |
-
value: 0.
|
52 |
- task:
|
53 |
name: LABELED_DEPENDENCIES
|
54 |
type: token-classification
|
55 |
metrics:
|
56 |
- name: Labeled Attachment Score (LAS)
|
57 |
type: f_score
|
58 |
-
value: 0.
|
59 |
- task:
|
60 |
name: SENTS
|
61 |
type: token-classification
|
62 |
metrics:
|
63 |
- name: Sentences F-Score
|
64 |
type: f_score
|
65 |
-
value:
|
66 |
---
|
67 |
### Details: https://spacy.io/models/ko#ko_core_news_md
|
68 |
|
@@ -71,12 +71,12 @@ Korean pipeline optimized for CPU. Components: tok2vec, tagger, morphologizer, p
|
|
71 |
| Feature | Description |
|
72 |
| --- | --- |
|
73 |
| **Name** | `ko_core_news_md` |
|
74 |
-
| **Version** | `3.
|
75 |
-
| **spaCy** | `>=3.
|
76 |
| **Default Pipeline** | `tok2vec`, `tagger`, `morphologizer`, `parser`, `lemmatizer`, `attribute_ruler`, `ner` |
|
77 |
| **Components** | `tok2vec`, `tagger`, `morphologizer`, `parser`, `lemmatizer`, `senter`, `attribute_ruler`, `ner` |
|
78 |
| **Vectors** | floret (50000, 300) |
|
79 |
-
| **Sources** | [UD Korean Kaist v2.8](https://github.com/UniversalDependencies/UD_Korean-Kaist) (Choi, Jinho; Han, Na-Rae; Hwang, Jena; Chun, Jayeol)<br />[KLUE v1.1.0](https://github.com/KLUE-benchmark/KLUE) (Sungjoon Park, Jihyung Moon, Sungdong Kim, Won Ik Cho, Jiyoon Han, Jangwon Park, Chisung Song, Junseong Kim, Youngsook Song, Taehwan Oh, Joohong Lee, Juhyun Oh, Sungwon Ryu, Younghoon Jeong, Inkwon Lee, Sangwoo Seo, Dongjun Lee, Hyunwoo Kim, Myeonghwa Lee, Seongbo Jang, Seungwon Do, Sunkyoung Kim, Kyungtae Lim, Jongwon Lee, Kyumin Park, Jamin Shin, Seonghyun Kim, Lucy Park, Alice Oh, Jung-Woo Ha, Kyunghyun Cho)<br />[Explosion
|
80 |
| **License** | `CC BY-SA 4.0` |
|
81 |
| **Author** | [Explosion](https://explosion.ai) |
|
82 |
|
@@ -84,12 +84,12 @@ Korean pipeline optimized for CPU. Components: tok2vec, tagger, morphologizer, p
|
|
84 |
|
85 |
<details>
|
86 |
|
87 |
-
<summary>View label scheme (
|
88 |
|
89 |
| Component | Labels |
|
90 |
| --- | --- |
|
91 |
-
| **`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`,
|
92 |
-
| **`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` |
|
93 |
| **`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` |
|
94 |
| **`ner`** | `DT`, `LC`, `OG`, `PS`, `QT`, `TI` |
|
95 |
|
@@ -103,14 +103,14 @@ Korean pipeline optimized for CPU. Components: tok2vec, tagger, morphologizer, p
|
|
103 |
| `TOKEN_P` | 100.00 |
|
104 |
| `TOKEN_R` | 100.00 |
|
105 |
| `TOKEN_F` | 100.00 |
|
106 |
-
| `TAG_ACC` | 83.
|
107 |
-
| `POS_ACC` | 94.
|
108 |
-
| `SENTS_P` |
|
109 |
-
| `SENTS_R` |
|
110 |
-
| `SENTS_F` |
|
111 |
-
| `DEP_UAS` | 83.
|
112 |
-
| `DEP_LAS` | 80.
|
113 |
-
| `LEMMA_ACC` | 89.
|
114 |
-
| `ENTS_P` |
|
115 |
-
| `ENTS_R` | 81.
|
116 |
-
| `ENTS_F` | 83.
|
|
|
14 |
metrics:
|
15 |
- name: NER Precision
|
16 |
type: precision
|
17 |
+
value: 0.8490038962
|
18 |
- name: NER Recall
|
19 |
type: recall
|
20 |
+
value: 0.8158954433
|
21 |
- name: NER F Score
|
22 |
type: f_score
|
23 |
+
value: 0.8321204698
|
24 |
- task:
|
25 |
name: TAG
|
26 |
type: token-classification
|
27 |
metrics:
|
28 |
- name: TAG (XPOS) Accuracy
|
29 |
type: accuracy
|
30 |
+
value: 0.8336399059
|
31 |
- task:
|
32 |
name: POS
|
33 |
type: token-classification
|
34 |
metrics:
|
35 |
- name: POS (UPOS) Accuracy
|
36 |
type: accuracy
|
37 |
+
value: 0.946239962
|
38 |
- task:
|
39 |
name: LEMMA
|
40 |
type: token-classification
|
41 |
metrics:
|
42 |
- name: Lemma Accuracy
|
43 |
type: accuracy
|
44 |
+
value: 0.8970905279
|
45 |
- task:
|
46 |
name: UNLABELED_DEPENDENCIES
|
47 |
type: token-classification
|
48 |
metrics:
|
49 |
- name: Unlabeled Attachment Score (UAS)
|
50 |
type: f_score
|
51 |
+
value: 0.83875855
|
52 |
- task:
|
53 |
name: LABELED_DEPENDENCIES
|
54 |
type: token-classification
|
55 |
metrics:
|
56 |
- name: Labeled Attachment Score (LAS)
|
57 |
type: f_score
|
58 |
+
value: 0.8092235713
|
59 |
- task:
|
60 |
name: SENTS
|
61 |
type: token-classification
|
62 |
metrics:
|
63 |
- name: Sentences F-Score
|
64 |
type: f_score
|
65 |
+
value: 0.9985486212
|
66 |
---
|
67 |
### Details: https://spacy.io/models/ko#ko_core_news_md
|
68 |
|
|
|
71 |
| Feature | Description |
|
72 |
| --- | --- |
|
73 |
| **Name** | `ko_core_news_md` |
|
74 |
+
| **Version** | `3.4.0` |
|
75 |
+
| **spaCy** | `>=3.4.0,<3.5.0` |
|
76 |
| **Default Pipeline** | `tok2vec`, `tagger`, `morphologizer`, `parser`, `lemmatizer`, `attribute_ruler`, `ner` |
|
77 |
| **Components** | `tok2vec`, `tagger`, `morphologizer`, `parser`, `lemmatizer`, `senter`, `attribute_ruler`, `ner` |
|
78 |
| **Vectors** | floret (50000, 300) |
|
79 |
+
| **Sources** | [UD Korean Kaist v2.8](https://github.com/UniversalDependencies/UD_Korean-Kaist) (Choi, Jinho; Han, Na-Rae; Hwang, Jena; Chun, Jayeol)<br />[KLUE v1.1.0](https://github.com/KLUE-benchmark/KLUE) (Sungjoon Park, Jihyung Moon, Sungdong Kim, Won Ik Cho, Jiyoon Han, Jangwon Park, Chisung Song, Junseong Kim, Youngsook Song, Taehwan Oh, Joohong Lee, Juhyun Oh, Sungwon Ryu, Younghoon Jeong, Inkwon Lee, Sangwoo Seo, Dongjun Lee, Hyunwoo Kim, Myeonghwa Lee, Seongbo Jang, Seungwon Do, Sunkyoung Kim, Kyungtae Lim, Jongwon Lee, Kyumin Park, Jamin Shin, Seonghyun Kim, Lucy Park, Alice Oh, Jung-Woo Ha, Kyunghyun Cho)<br />[Explosion Vectors (OSCAR 2109 + Wikipedia + OpenSubtitles + WMT News Crawl)](https://github.com/explosion/spacy-vectors-builder) (Explosion) |
|
80 |
| **License** | `CC BY-SA 4.0` |
|
81 |
| **Author** | [Explosion](https://explosion.ai) |
|
82 |
|
|
|
84 |
|
85 |
<details>
|
86 |
|
87 |
+
<summary>View label scheme (2028 labels for 4 components)</summary>
|
88 |
|
89 |
| Component | Labels |
|
90 |
| --- | --- |
|
91 |
+
| **`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)_ |
|
92 |
+
| **`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` |
|
93 |
| **`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` |
|
94 |
| **`ner`** | `DT`, `LC`, `OG`, `PS`, `QT`, `TI` |
|
95 |
|
|
|
103 |
| `TOKEN_P` | 100.00 |
|
104 |
| `TOKEN_R` | 100.00 |
|
105 |
| `TOKEN_F` | 100.00 |
|
106 |
+
| `TAG_ACC` | 83.36 |
|
107 |
+
| `POS_ACC` | 94.62 |
|
108 |
+
| `SENTS_P` | 99.81 |
|
109 |
+
| `SENTS_R` | 99.90 |
|
110 |
+
| `SENTS_F` | 99.85 |
|
111 |
+
| `DEP_UAS` | 83.88 |
|
112 |
+
| `DEP_LAS` | 80.92 |
|
113 |
+
| `LEMMA_ACC` | 89.71 |
|
114 |
+
| `ENTS_P` | 84.90 |
|
115 |
+
| `ENTS_R` | 81.59 |
|
116 |
+
| `ENTS_F` | 83.21 |
|
accuracy.json
CHANGED
@@ -3,113 +3,113 @@
|
|
3 |
"token_p": 1.0,
|
4 |
"token_r": 1.0,
|
5 |
"token_f": 1.0,
|
6 |
-
"tag_acc": 0.
|
7 |
-
"pos_acc": 0.
|
8 |
-
"sents_p":
|
9 |
-
"sents_r":
|
10 |
-
"sents_f":
|
11 |
-
"dep_uas": 0.
|
12 |
-
"dep_las": 0.
|
13 |
"dep_las_per_type": {
|
14 |
"amod": {
|
15 |
-
"p": 0.
|
16 |
-
"r": 0.
|
17 |
-
"f": 0.
|
18 |
},
|
19 |
"dislocated": {
|
20 |
-
"p": 0.
|
21 |
-
"r": 0.
|
22 |
-
"f": 0.
|
23 |
},
|
24 |
"root": {
|
25 |
-
"p": 0.
|
26 |
-
"r": 0.
|
27 |
-
"f": 0.
|
28 |
},
|
29 |
"nmod": {
|
30 |
-
"p": 0.
|
31 |
-
"r": 0.
|
32 |
-
"f": 0.
|
33 |
},
|
34 |
"nsubj": {
|
35 |
-
"p": 0.
|
36 |
-
"r": 0.
|
37 |
-
"f": 0.
|
38 |
},
|
39 |
"advmod": {
|
40 |
-
"p": 0.
|
41 |
-
"r": 0.
|
42 |
-
"f": 0.
|
43 |
},
|
44 |
"dep": {
|
45 |
-
"p": 0.
|
46 |
-
"r": 0.
|
47 |
-
"f": 0.
|
48 |
},
|
49 |
"conj": {
|
50 |
-
"p": 0.
|
51 |
-
"r": 0.
|
52 |
-
"f": 0.
|
53 |
},
|
54 |
"xcomp": {
|
55 |
-
"p": 0.
|
56 |
-
"r": 0.
|
57 |
-
"f": 0.
|
58 |
},
|
59 |
"flat": {
|
60 |
-
"p": 0.
|
61 |
-
"r": 0.
|
62 |
-
"f": 0.
|
63 |
},
|
64 |
"obj": {
|
65 |
-
"p": 0.
|
66 |
-
"r": 0.
|
67 |
-
"f": 0.
|
68 |
},
|
69 |
"acl": {
|
70 |
-
"p": 0.
|
71 |
-
"r": 0.
|
72 |
-
"f": 0.
|
73 |
},
|
74 |
"advcl": {
|
75 |
-
"p": 0.
|
76 |
-
"r": 0.
|
77 |
-
"f": 0.
|
78 |
},
|
79 |
"det": {
|
80 |
-
"p": 0.
|
81 |
-
"r": 0.
|
82 |
-
"f": 0.
|
83 |
},
|
84 |
"compound": {
|
85 |
-
"p": 0.
|
86 |
-
"r": 0.
|
87 |
-
"f": 0.
|
88 |
},
|
89 |
"ccomp": {
|
90 |
-
"p": 0.
|
91 |
-
"r": 0.
|
92 |
-
"f": 0.
|
93 |
},
|
94 |
"obl": {
|
95 |
-
"p": 0.
|
96 |
-
"r": 0.
|
97 |
-
"f": 0.
|
98 |
},
|
99 |
"aux": {
|
100 |
-
"p": 0.
|
101 |
-
"r": 0.
|
102 |
-
"f": 0.
|
103 |
},
|
104 |
"cc": {
|
105 |
-
"p": 0.
|
106 |
-
"r": 0.
|
107 |
-
"f": 0.
|
108 |
},
|
109 |
"nummod": {
|
110 |
-
"p": 0.
|
111 |
-
"r": 0.
|
112 |
-
"f": 0.
|
113 |
},
|
114 |
"discourse": {
|
115 |
"p": 0.0,
|
@@ -117,34 +117,34 @@
|
|
117 |
"f": 0.0
|
118 |
},
|
119 |
"fixed": {
|
120 |
-
"p": 0.
|
121 |
-
"r": 0
|
122 |
-
"f": 0.
|
123 |
},
|
124 |
"csubj": {
|
125 |
-
"p": 0.
|
126 |
-
"r": 0.
|
127 |
-
"f": 0.
|
128 |
},
|
129 |
"mark": {
|
130 |
-
"p": 0.
|
131 |
-
"r": 0.
|
132 |
-
"f": 0.
|
133 |
},
|
134 |
"iobj": {
|
135 |
-
"p": 0.
|
136 |
-
"r": 0.
|
137 |
-
"f": 0.
|
138 |
},
|
139 |
"case": {
|
140 |
-
"p": 0.
|
141 |
-
"r": 0.
|
142 |
-
"f": 0.
|
143 |
},
|
144 |
"cop": {
|
145 |
-
"p": 0.
|
146 |
-
"r": 0.
|
147 |
-
"f": 0.
|
148 |
},
|
149 |
"vocative": {
|
150 |
"p": 0.0,
|
@@ -152,46 +152,46 @@
|
|
152 |
"f": 0.0
|
153 |
},
|
154 |
"appos": {
|
155 |
-
"p": 0.
|
156 |
"r": 0.7142857143,
|
157 |
-
"f": 0.
|
158 |
}
|
159 |
},
|
160 |
-
"lemma_acc": 0.
|
161 |
-
"speed":
|
162 |
-
"ents_p": 0.
|
163 |
-
"ents_r": 0.
|
164 |
-
"ents_f": 0.
|
165 |
"ents_per_type": {
|
166 |
"OG": {
|
167 |
-
"p": 0.
|
168 |
-
"r": 0.
|
169 |
-
"f": 0.
|
170 |
},
|
171 |
"PS": {
|
172 |
-
"p": 0.
|
173 |
-
"r": 0.
|
174 |
-
"f": 0.
|
175 |
},
|
176 |
"QT": {
|
177 |
-
"p": 0.
|
178 |
-
"r": 0.
|
179 |
-
"f": 0.
|
180 |
},
|
181 |
"DT": {
|
182 |
-
"p": 0.
|
183 |
-
"r": 0.
|
184 |
-
"f": 0.
|
185 |
},
|
186 |
"LC": {
|
187 |
-
"p": 0.
|
188 |
-
"r": 0.
|
189 |
-
"f": 0.
|
190 |
},
|
191 |
"TI": {
|
192 |
-
"p": 0.
|
193 |
-
"r": 0.
|
194 |
-
"f": 0.
|
195 |
}
|
196 |
}
|
197 |
}
|
|
|
3 |
"token_p": 1.0,
|
4 |
"token_r": 1.0,
|
5 |
"token_f": 1.0,
|
6 |
+
"tag_acc": 0.8336399059,
|
7 |
+
"pos_acc": 0.946239962,
|
8 |
+
"sents_p": 0.998065764,
|
9 |
+
"sents_r": 0.9990319458,
|
10 |
+
"sents_f": 0.9985486212,
|
11 |
+
"dep_uas": 0.83875855,
|
12 |
+
"dep_las": 0.8092235713,
|
13 |
"dep_las_per_type": {
|
14 |
"amod": {
|
15 |
+
"p": 0.8202443281,
|
16 |
+
"r": 0.823117338,
|
17 |
+
"f": 0.8216783217
|
18 |
},
|
19 |
"dislocated": {
|
20 |
+
"p": 0.7434725849,
|
21 |
+
"r": 0.7405721717,
|
22 |
+
"f": 0.742019544
|
23 |
},
|
24 |
"root": {
|
25 |
+
"p": 0.8689555126,
|
26 |
+
"r": 0.8697967086,
|
27 |
+
"f": 0.8693759071
|
28 |
},
|
29 |
"nmod": {
|
30 |
+
"p": 0.8883610451,
|
31 |
+
"r": 0.8878338279,
|
32 |
+
"f": 0.8880973583
|
33 |
},
|
34 |
"nsubj": {
|
35 |
+
"p": 0.7961089494,
|
36 |
+
"r": 0.8157894737,
|
37 |
+
"f": 0.8058290666
|
38 |
},
|
39 |
"advmod": {
|
40 |
+
"p": 0.7191097467,
|
41 |
+
"r": 0.7354788069,
|
42 |
+
"f": 0.7272021731
|
43 |
},
|
44 |
"dep": {
|
45 |
+
"p": 0.6642335766,
|
46 |
+
"r": 0.5027624309,
|
47 |
+
"f": 0.572327044
|
48 |
},
|
49 |
"conj": {
|
50 |
+
"p": 0.7157057654,
|
51 |
+
"r": 0.6923076923,
|
52 |
+
"f": 0.7038123167
|
53 |
},
|
54 |
"xcomp": {
|
55 |
+
"p": 0.6344827586,
|
56 |
+
"r": 0.6323024055,
|
57 |
+
"f": 0.6333907057
|
58 |
},
|
59 |
"flat": {
|
60 |
+
"p": 0.625,
|
61 |
+
"r": 0.1869158879,
|
62 |
+
"f": 0.2877697842
|
63 |
},
|
64 |
"obj": {
|
65 |
+
"p": 0.9232832618,
|
66 |
+
"r": 0.9247716282,
|
67 |
+
"f": 0.9240268456
|
68 |
},
|
69 |
"acl": {
|
70 |
+
"p": 0.8018072289,
|
71 |
+
"r": 0.7984403119,
|
72 |
+
"f": 0.8001202284
|
73 |
},
|
74 |
"advcl": {
|
75 |
+
"p": 0.7902571042,
|
76 |
+
"r": 0.7929395791,
|
77 |
+
"f": 0.7915960691
|
78 |
},
|
79 |
"det": {
|
80 |
+
"p": 0.7652733119,
|
81 |
+
"r": 0.8947368421,
|
82 |
+
"f": 0.8249566724
|
83 |
},
|
84 |
"compound": {
|
85 |
+
"p": 0.7985823981,
|
86 |
+
"r": 0.8253968254,
|
87 |
+
"f": 0.8117682378
|
88 |
},
|
89 |
"ccomp": {
|
90 |
+
"p": 0.6488925349,
|
91 |
+
"r": 0.6564315353,
|
92 |
+
"f": 0.652640264
|
93 |
},
|
94 |
"obl": {
|
95 |
+
"p": 0.8827493261,
|
96 |
+
"r": 0.8935879945,
|
97 |
+
"f": 0.8881355932
|
98 |
},
|
99 |
"aux": {
|
100 |
+
"p": 0.9286713287,
|
101 |
+
"r": 0.9312762973,
|
102 |
+
"f": 0.9299719888
|
103 |
},
|
104 |
"cc": {
|
105 |
+
"p": 0.8193548387,
|
106 |
+
"r": 0.8410596026,
|
107 |
+
"f": 0.8300653595
|
108 |
},
|
109 |
"nummod": {
|
110 |
+
"p": 0.8540540541,
|
111 |
+
"r": 0.8272251309,
|
112 |
+
"f": 0.8404255319
|
113 |
},
|
114 |
"discourse": {
|
115 |
"p": 0.0,
|
|
|
117 |
"f": 0.0
|
118 |
},
|
119 |
"fixed": {
|
120 |
+
"p": 0.956,
|
121 |
+
"r": 1.0,
|
122 |
+
"f": 0.9775051125
|
123 |
},
|
124 |
"csubj": {
|
125 |
+
"p": 0.5393258427,
|
126 |
+
"r": 0.4363636364,
|
127 |
+
"f": 0.4824120603
|
128 |
},
|
129 |
"mark": {
|
130 |
+
"p": 0.6923076923,
|
131 |
+
"r": 0.5538461538,
|
132 |
+
"f": 0.6153846154
|
133 |
},
|
134 |
"iobj": {
|
135 |
+
"p": 0.8169014085,
|
136 |
+
"r": 0.8169014085,
|
137 |
+
"f": 0.8169014085
|
138 |
},
|
139 |
"case": {
|
140 |
+
"p": 0.8260869565,
|
141 |
+
"r": 0.8382352941,
|
142 |
+
"f": 0.8321167883
|
143 |
},
|
144 |
"cop": {
|
145 |
+
"p": 0.6666666667,
|
146 |
+
"r": 0.6666666667,
|
147 |
+
"f": 0.6666666667
|
148 |
},
|
149 |
"vocative": {
|
150 |
"p": 0.0,
|
|
|
152 |
"f": 0.0
|
153 |
},
|
154 |
"appos": {
|
155 |
+
"p": 0.7142857143,
|
156 |
"r": 0.7142857143,
|
157 |
+
"f": 0.7142857143
|
158 |
}
|
159 |
},
|
160 |
+
"lemma_acc": 0.8970905279,
|
161 |
+
"speed": 5125.497744352,
|
162 |
+
"ents_p": 0.8490038962,
|
163 |
+
"ents_r": 0.8158954433,
|
164 |
+
"ents_f": 0.8321204698,
|
165 |
"ents_per_type": {
|
166 |
"OG": {
|
167 |
+
"p": 0.7671443193,
|
168 |
+
"r": 0.6949466852,
|
169 |
+
"f": 0.7292629531
|
170 |
},
|
171 |
"PS": {
|
172 |
+
"p": 0.859375,
|
173 |
+
"r": 0.7998182231,
|
174 |
+
"f": 0.8285277157
|
175 |
},
|
176 |
"QT": {
|
177 |
+
"p": 0.9160861305,
|
178 |
+
"r": 0.9275408785,
|
179 |
+
"f": 0.9217779194
|
180 |
},
|
181 |
"DT": {
|
182 |
+
"p": 0.8884462151,
|
183 |
+
"r": 0.8699609883,
|
184 |
+
"f": 0.8791064389
|
185 |
},
|
186 |
"LC": {
|
187 |
+
"p": 0.7082294264,
|
188 |
+
"r": 0.6986469865,
|
189 |
+
"f": 0.7034055728
|
190 |
},
|
191 |
"TI": {
|
192 |
+
"p": 0.9285714286,
|
193 |
+
"r": 0.9064220183,
|
194 |
+
"f": 0.9173630455
|
195 |
}
|
196 |
}
|
197 |
}
|
ko_core_news_md-any-py3-none-any.whl
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a92de93f560fa9352b87c71a93da1462c042752ab6dee2578b073c19f9c3559
|
3 |
+
size 69054189
|
lemmatizer/cfg
CHANGED
@@ -903,250 +903,243 @@
|
|
903 |
1708,
|
904 |
1709,
|
905 |
1711,
|
906 |
-
|
907 |
1716,
|
908 |
-
|
909 |
-
|
910 |
-
|
911 |
-
|
912 |
-
|
913 |
1729,
|
|
|
914 |
1731,
|
915 |
-
|
916 |
-
|
917 |
-
1736,
|
918 |
1739,
|
919 |
-
|
920 |
1744,
|
921 |
1746,
|
922 |
-
|
923 |
-
|
924 |
1754,
|
925 |
-
|
926 |
-
|
927 |
1764,
|
928 |
-
|
929 |
1769,
|
930 |
1771,
|
931 |
1773,
|
932 |
-
1775,
|
933 |
120,
|
934 |
-
|
|
|
935 |
1778,
|
936 |
-
|
937 |
1783,
|
938 |
-
|
939 |
1786,
|
940 |
1788,
|
|
|
941 |
1790,
|
942 |
-
1791,
|
943 |
1792,
|
944 |
1794,
|
945 |
1796,
|
946 |
1798,
|
947 |
-
|
948 |
1803,
|
949 |
-
|
950 |
1806,
|
951 |
-
|
952 |
-
|
953 |
1812,
|
954 |
-
1814,
|
955 |
888,
|
|
|
|
|
956 |
1816,
|
957 |
1817,
|
958 |
-
|
959 |
-
|
960 |
-
|
961 |
-
1825,
|
962 |
-
1828,
|
963 |
1700,
|
964 |
-
|
965 |
-
|
966 |
-
|
967 |
-
|
|
|
968 |
1840,
|
969 |
-
|
970 |
-
|
971 |
1848,
|
972 |
1850,
|
973 |
-
|
974 |
1855,
|
|
|
975 |
1857,
|
976 |
-
|
977 |
-
1861,
|
978 |
1862,
|
979 |
-
|
980 |
1865,
|
981 |
1867,
|
982 |
-
|
983 |
1870,
|
984 |
1872,
|
985 |
-
|
986 |
-
|
987 |
-
|
988 |
-
1879,
|
989 |
1881,
|
990 |
-
|
991 |
1885,
|
992 |
-
|
993 |
1889,
|
994 |
-
|
995 |
-
|
|
|
996 |
1898,
|
997 |
1900,
|
998 |
-
|
999 |
-
|
1000 |
-
1905,
|
1001 |
1907,
|
|
|
1002 |
1910,
|
1003 |
-
|
1004 |
1913,
|
1005 |
-
|
1006 |
-
|
1007 |
1920,
|
1008 |
-
1922,
|
1009 |
1923,
|
|
|
1010 |
1926,
|
1011 |
1928,
|
1012 |
1929,
|
1013 |
-
1931,
|
1014 |
1932,
|
1015 |
-
|
1016 |
1936,
|
1017 |
-
|
1018 |
1941,
|
1019 |
-
|
1020 |
-
|
1021 |
-
|
1022 |
1950,
|
1023 |
-
|
|
|
1024 |
1955,
|
1025 |
-
|
1026 |
1958,
|
1027 |
-
1959,
|
1028 |
1961,
|
|
|
1029 |
1964,
|
1030 |
-
1966,
|
1031 |
1967,
|
|
|
1032 |
1970,
|
1033 |
1971,
|
1034 |
1973,
|
1035 |
-
|
1036 |
-
|
1037 |
-
|
1038 |
-
1981,
|
1039 |
1982,
|
1040 |
-
|
1041 |
-
|
1042 |
-
|
1043 |
-
|
1044 |
-
|
1045 |
-
1995,
|
1046 |
109,
|
1047 |
-
|
|
|
1048 |
1999,
|
|
|
1049 |
2002,
|
1050 |
2004,
|
1051 |
-
2005,
|
1052 |
2007,
|
1053 |
-
|
|
|
1054 |
2011,
|
1055 |
-
|
1056 |
-
|
1057 |
-
2016,
|
1058 |
2018,
|
|
|
1059 |
2021,
|
1060 |
-
|
1061 |
2024,
|
1062 |
-
2025,
|
1063 |
2027,
|
1064 |
-
|
1065 |
-
|
|
|
1066 |
2035,
|
1067 |
-
2036,
|
1068 |
2038,
|
|
|
1069 |
2041,
|
1070 |
2042,
|
1071 |
-
2044,
|
1072 |
2045,
|
|
|
1073 |
2048,
|
1074 |
2049,
|
1075 |
2051,
|
1076 |
-
|
1077 |
-
|
1078 |
2056,
|
1079 |
2058,
|
1080 |
-
|
1081 |
-
|
1082 |
-
|
1083 |
-
|
1084 |
2067,
|
1085 |
2069,
|
1086 |
-
|
1087 |
-
2072,
|
1088 |
2074,
|
1089 |
-
|
1090 |
2079,
|
1091 |
-
|
1092 |
-
|
1093 |
-
2085,
|
1094 |
-
2088,
|
1095 |
911,
|
|
|
|
|
1096 |
2089,
|
1097 |
-
|
|
|
1098 |
2094,
|
1099 |
-
|
1100 |
-
|
1101 |
-
|
1102 |
-
|
1103 |
-
|
1104 |
-
|
1105 |
-
|
1106 |
-
2115,
|
1107 |
2117,
|
1108 |
-
|
1109 |
-
|
1110 |
-
|
1111 |
2126,
|
1112 |
-
|
1113 |
-
|
1114 |
2132,
|
1115 |
2133,
|
1116 |
-
|
1117 |
-
|
|
|
|
|
1118 |
2139,
|
1119 |
2140,
|
1120 |
-
2141,
|
1121 |
2143,
|
1122 |
-
611,
|
1123 |
2145,
|
1124 |
-
|
1125 |
2149,
|
1126 |
2151,
|
1127 |
2153,
|
1128 |
-
|
1129 |
2157,
|
|
|
1130 |
2159,
|
1131 |
-
|
1132 |
2164,
|
1133 |
-
2165,
|
1134 |
-
2166,
|
1135 |
2167,
|
1136 |
-
|
1137 |
2172,
|
1138 |
2175,
|
1139 |
2178,
|
1140 |
2180,
|
|
|
1141 |
2183,
|
|
|
1142 |
2186,
|
1143 |
-
2188
|
1144 |
-
2190,
|
1145 |
-
2191,
|
1146 |
-
2193,
|
1147 |
-
2194,
|
1148 |
-
2196,
|
1149 |
-
2197,
|
1150 |
-
2199
|
1151 |
]
|
1152 |
}
|
|
|
903 |
1708,
|
904 |
1709,
|
905 |
1711,
|
906 |
+
1714,
|
907 |
1716,
|
908 |
+
1719,
|
909 |
+
1720,
|
910 |
+
1723,
|
911 |
+
1726,
|
912 |
+
1727,
|
913 |
1729,
|
914 |
+
1730,
|
915 |
1731,
|
916 |
+
1734,
|
917 |
+
1737,
|
|
|
918 |
1739,
|
919 |
+
1742,
|
920 |
1744,
|
921 |
1746,
|
922 |
+
1749,
|
923 |
+
1752,
|
924 |
1754,
|
925 |
+
1759,
|
926 |
+
1762,
|
927 |
1764,
|
928 |
+
1767,
|
929 |
1769,
|
930 |
1771,
|
931 |
1773,
|
|
|
932 |
120,
|
933 |
+
1775,
|
934 |
+
1776,
|
935 |
1778,
|
936 |
+
1781,
|
937 |
1783,
|
938 |
+
1784,
|
939 |
1786,
|
940 |
1788,
|
941 |
+
1789,
|
942 |
1790,
|
|
|
943 |
1792,
|
944 |
1794,
|
945 |
1796,
|
946 |
1798,
|
947 |
+
1801,
|
948 |
1803,
|
949 |
+
1804,
|
950 |
1806,
|
951 |
+
1809,
|
952 |
+
1810,
|
953 |
1812,
|
|
|
954 |
888,
|
955 |
+
1814,
|
956 |
+
1815,
|
957 |
1816,
|
958 |
1817,
|
959 |
+
1820,
|
960 |
+
1823,
|
961 |
+
1826,
|
|
|
|
|
962 |
1700,
|
963 |
+
1828,
|
964 |
+
1831,
|
965 |
+
1832,
|
966 |
+
1835,
|
967 |
+
1838,
|
968 |
1840,
|
969 |
+
1843,
|
970 |
+
1846,
|
971 |
1848,
|
972 |
1850,
|
973 |
+
1852,
|
974 |
1855,
|
975 |
+
1856,
|
976 |
1857,
|
977 |
+
1859,
|
|
|
978 |
1862,
|
979 |
+
1864,
|
980 |
1865,
|
981 |
1867,
|
982 |
+
1869,
|
983 |
1870,
|
984 |
1872,
|
985 |
+
1874,
|
986 |
+
1876,
|
987 |
+
1878,
|
|
|
988 |
1881,
|
989 |
+
1882,
|
990 |
1885,
|
991 |
+
1886,
|
992 |
1889,
|
993 |
+
1891,
|
994 |
+
1895,
|
995 |
+
1897,
|
996 |
1898,
|
997 |
1900,
|
998 |
+
1902,
|
999 |
+
1904,
|
|
|
1000 |
1907,
|
1001 |
+
1908,
|
1002 |
1910,
|
1003 |
+
1912,
|
1004 |
1913,
|
1005 |
+
1917,
|
1006 |
+
1919,
|
1007 |
1920,
|
|
|
1008 |
1923,
|
1009 |
+
1925,
|
1010 |
1926,
|
1011 |
1928,
|
1012 |
1929,
|
|
|
1013 |
1932,
|
1014 |
+
1933,
|
1015 |
1936,
|
1016 |
+
1938,
|
1017 |
1941,
|
1018 |
+
1943,
|
1019 |
+
1945,
|
1020 |
+
1947,
|
1021 |
1950,
|
1022 |
+
1952,
|
1023 |
+
1954,
|
1024 |
1955,
|
1025 |
+
1956,
|
1026 |
1958,
|
|
|
1027 |
1961,
|
1028 |
+
1963,
|
1029 |
1964,
|
|
|
1030 |
1967,
|
1031 |
+
1968,
|
1032 |
1970,
|
1033 |
1971,
|
1034 |
1973,
|
1035 |
+
1977,
|
1036 |
+
1978,
|
1037 |
+
1979,
|
|
|
1038 |
1982,
|
1039 |
+
1984,
|
1040 |
+
1986,
|
1041 |
+
1988,
|
1042 |
+
1990,
|
1043 |
+
1992,
|
|
|
1044 |
109,
|
1045 |
+
1994,
|
1046 |
+
1996,
|
1047 |
1999,
|
1048 |
+
2001,
|
1049 |
2002,
|
1050 |
2004,
|
|
|
1051 |
2007,
|
1052 |
+
2008,
|
1053 |
+
2009,
|
1054 |
2011,
|
1055 |
+
2013,
|
1056 |
+
2015,
|
|
|
1057 |
2018,
|
1058 |
+
2020,
|
1059 |
2021,
|
1060 |
+
2022,
|
1061 |
2024,
|
|
|
1062 |
2027,
|
1063 |
+
2028,
|
1064 |
+
2032,
|
1065 |
+
2033,
|
1066 |
2035,
|
|
|
1067 |
2038,
|
1068 |
+
2039,
|
1069 |
2041,
|
1070 |
2042,
|
|
|
1071 |
2045,
|
1072 |
+
2046,
|
1073 |
2048,
|
1074 |
2049,
|
1075 |
2051,
|
1076 |
+
2053,
|
1077 |
+
2055,
|
1078 |
2056,
|
1079 |
2058,
|
1080 |
+
2060,
|
1081 |
+
2062,
|
1082 |
+
2064,
|
1083 |
+
2066,
|
1084 |
2067,
|
1085 |
2069,
|
1086 |
+
2071,
|
|
|
1087 |
2074,
|
1088 |
+
2076,
|
1089 |
2079,
|
1090 |
+
2080,
|
1091 |
+
2083,
|
|
|
|
|
1092 |
911,
|
1093 |
+
2084,
|
1094 |
+
2087,
|
1095 |
2089,
|
1096 |
+
2091,
|
1097 |
+
2093,
|
1098 |
2094,
|
1099 |
+
2097,
|
1100 |
+
2100,
|
1101 |
+
2104,
|
1102 |
+
2108,
|
1103 |
+
2110,
|
1104 |
+
2112,
|
1105 |
+
2114,
|
|
|
1106 |
2117,
|
1107 |
+
2120,
|
1108 |
+
2121,
|
1109 |
+
2123,
|
1110 |
2126,
|
1111 |
+
2127,
|
1112 |
+
2130,
|
1113 |
2132,
|
1114 |
2133,
|
1115 |
+
2134,
|
1116 |
+
2135,
|
1117 |
+
2137,
|
1118 |
+
611,
|
1119 |
2139,
|
1120 |
2140,
|
|
|
1121 |
2143,
|
|
|
1122 |
2145,
|
1123 |
+
2147,
|
1124 |
2149,
|
1125 |
2151,
|
1126 |
2153,
|
1127 |
+
2156,
|
1128 |
2157,
|
1129 |
+
2158,
|
1130 |
2159,
|
1131 |
+
2163,
|
1132 |
2164,
|
|
|
|
|
1133 |
2167,
|
1134 |
+
2170,
|
1135 |
2172,
|
1136 |
2175,
|
1137 |
2178,
|
1138 |
2180,
|
1139 |
+
2182,
|
1140 |
2183,
|
1141 |
+
2185,
|
1142 |
2186,
|
1143 |
+
2188
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1144 |
]
|
1145 |
}
|
lemmatizer/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e184e0f2adc0f8513bb75dbcd61dc981ca0f9f94a96ba73bdc72b2000b36f879
|
3 |
+
size 443150
|
lemmatizer/trees
CHANGED
Binary files a/lemmatizer/trees and b/lemmatizer/trees differ
|
|
meta.json
CHANGED
@@ -1,14 +1,14 @@
|
|
1 |
{
|
2 |
"lang":"ko",
|
3 |
"name":"core_news_md",
|
4 |
-
"version":"3.
|
5 |
"description":"Korean pipeline optimized for CPU. Components: tok2vec, tagger, morphologizer, parser, lemmatizer (trainable_lemmatizer), senter, ner.",
|
6 |
"author":"Explosion",
|
7 |
"email":"contact@explosion.ai",
|
8 |
"url":"https://explosion.ai",
|
9 |
"license":"CC BY-SA 4.0",
|
10 |
-
"spacy_version":">=3.
|
11 |
-
"spacy_git_version":"
|
12 |
"vectors":{
|
13 |
"width":300,
|
14 |
"vectors":50000,
|
@@ -20,6 +20,7 @@
|
|
20 |
|
21 |
],
|
22 |
"tagger":[
|
|
|
23 |
"ecs",
|
24 |
"etm",
|
25 |
"f",
|
@@ -2005,6 +2006,7 @@
|
|
2005 |
"POS=VERB",
|
2006 |
"POS=ADJ",
|
2007 |
"POS=PUNCT",
|
|
|
2008 |
"POS=AUX",
|
2009 |
"POS=PRON",
|
2010 |
"POS=PROPN",
|
@@ -2084,113 +2086,113 @@
|
|
2084 |
"token_p":1.0,
|
2085 |
"token_r":1.0,
|
2086 |
"token_f":1.0,
|
2087 |
-
"tag_acc":0.
|
2088 |
-
"pos_acc":0.
|
2089 |
-
"sents_p":
|
2090 |
-
"sents_r":
|
2091 |
-
"sents_f":
|
2092 |
-
"dep_uas":0.
|
2093 |
-
"dep_las":0.
|
2094 |
"dep_las_per_type":{
|
2095 |
"amod":{
|
2096 |
-
"p":0.
|
2097 |
-
"r":0.
|
2098 |
-
"f":0.
|
2099 |
},
|
2100 |
"dislocated":{
|
2101 |
-
"p":0.
|
2102 |
-
"r":0.
|
2103 |
-
"f":0.
|
2104 |
},
|
2105 |
"root":{
|
2106 |
-
"p":0.
|
2107 |
-
"r":0.
|
2108 |
-
"f":0.
|
2109 |
},
|
2110 |
"nmod":{
|
2111 |
-
"p":0.
|
2112 |
-
"r":0.
|
2113 |
-
"f":0.
|
2114 |
},
|
2115 |
"nsubj":{
|
2116 |
-
"p":0.
|
2117 |
-
"r":0.
|
2118 |
-
"f":0.
|
2119 |
},
|
2120 |
"advmod":{
|
2121 |
-
"p":0.
|
2122 |
-
"r":0.
|
2123 |
-
"f":0.
|
2124 |
},
|
2125 |
"dep":{
|
2126 |
-
"p":0.
|
2127 |
-
"r":0.
|
2128 |
-
"f":0.
|
2129 |
},
|
2130 |
"conj":{
|
2131 |
-
"p":0.
|
2132 |
-
"r":0.
|
2133 |
-
"f":0.
|
2134 |
},
|
2135 |
"xcomp":{
|
2136 |
-
"p":0.
|
2137 |
-
"r":0.
|
2138 |
-
"f":0.
|
2139 |
},
|
2140 |
"flat":{
|
2141 |
-
"p":0.
|
2142 |
-
"r":0.
|
2143 |
-
"f":0.
|
2144 |
},
|
2145 |
"obj":{
|
2146 |
-
"p":0.
|
2147 |
-
"r":0.
|
2148 |
-
"f":0.
|
2149 |
},
|
2150 |
"acl":{
|
2151 |
-
"p":0.
|
2152 |
-
"r":0.
|
2153 |
-
"f":0.
|
2154 |
},
|
2155 |
"advcl":{
|
2156 |
-
"p":0.
|
2157 |
-
"r":0.
|
2158 |
-
"f":0.
|
2159 |
},
|
2160 |
"det":{
|
2161 |
-
"p":0.
|
2162 |
-
"r":0.
|
2163 |
-
"f":0.
|
2164 |
},
|
2165 |
"compound":{
|
2166 |
-
"p":0.
|
2167 |
-
"r":0.
|
2168 |
-
"f":0.
|
2169 |
},
|
2170 |
"ccomp":{
|
2171 |
-
"p":0.
|
2172 |
-
"r":0.
|
2173 |
-
"f":0.
|
2174 |
},
|
2175 |
"obl":{
|
2176 |
-
"p":0.
|
2177 |
-
"r":0.
|
2178 |
-
"f":0.
|
2179 |
},
|
2180 |
"aux":{
|
2181 |
-
"p":0.
|
2182 |
-
"r":0.
|
2183 |
-
"f":0.
|
2184 |
},
|
2185 |
"cc":{
|
2186 |
-
"p":0.
|
2187 |
-
"r":0.
|
2188 |
-
"f":0.
|
2189 |
},
|
2190 |
"nummod":{
|
2191 |
-
"p":0.
|
2192 |
-
"r":0.
|
2193 |
-
"f":0.
|
2194 |
},
|
2195 |
"discourse":{
|
2196 |
"p":0.0,
|
@@ -2198,34 +2200,34 @@
|
|
2198 |
"f":0.0
|
2199 |
},
|
2200 |
"fixed":{
|
2201 |
-
"p":0.
|
2202 |
-
"r":0
|
2203 |
-
"f":0.
|
2204 |
},
|
2205 |
"csubj":{
|
2206 |
-
"p":0.
|
2207 |
-
"r":0.
|
2208 |
-
"f":0.
|
2209 |
},
|
2210 |
"mark":{
|
2211 |
-
"p":0.
|
2212 |
-
"r":0.
|
2213 |
-
"f":0.
|
2214 |
},
|
2215 |
"iobj":{
|
2216 |
-
"p":0.
|
2217 |
-
"r":0.
|
2218 |
-
"f":0.
|
2219 |
},
|
2220 |
"case":{
|
2221 |
-
"p":0.
|
2222 |
-
"r":0.
|
2223 |
-
"f":0.
|
2224 |
},
|
2225 |
"cop":{
|
2226 |
-
"p":0.
|
2227 |
-
"r":0.
|
2228 |
-
"f":0.
|
2229 |
},
|
2230 |
"vocative":{
|
2231 |
"p":0.0,
|
@@ -2233,46 +2235,46 @@
|
|
2233 |
"f":0.0
|
2234 |
},
|
2235 |
"appos":{
|
2236 |
-
"p":0.
|
2237 |
"r":0.7142857143,
|
2238 |
-
"f":0.
|
2239 |
}
|
2240 |
},
|
2241 |
-
"lemma_acc":0.
|
2242 |
-
"speed":
|
2243 |
-
"ents_p":0.
|
2244 |
-
"ents_r":0.
|
2245 |
-
"ents_f":0.
|
2246 |
"ents_per_type":{
|
2247 |
"OG":{
|
2248 |
-
"p":0.
|
2249 |
-
"r":0.
|
2250 |
-
"f":0.
|
2251 |
},
|
2252 |
"PS":{
|
2253 |
-
"p":0.
|
2254 |
-
"r":0.
|
2255 |
-
"f":0.
|
2256 |
},
|
2257 |
"QT":{
|
2258 |
-
"p":0.
|
2259 |
-
"r":0.
|
2260 |
-
"f":0.
|
2261 |
},
|
2262 |
"DT":{
|
2263 |
-
"p":0.
|
2264 |
-
"r":0.
|
2265 |
-
"f":0.
|
2266 |
},
|
2267 |
"LC":{
|
2268 |
-
"p":0.
|
2269 |
-
"r":0.
|
2270 |
-
"f":0.
|
2271 |
},
|
2272 |
"TI":{
|
2273 |
-
"p":0.
|
2274 |
-
"r":0.
|
2275 |
-
"f":0.
|
2276 |
}
|
2277 |
}
|
2278 |
},
|
@@ -2290,7 +2292,7 @@
|
|
2290 |
"author":"Sungjoon Park, Jihyung Moon, Sungdong Kim, Won Ik Cho, Jiyoon Han, Jangwon Park, Chisung Song, Junseong Kim, Youngsook Song, Taehwan Oh, Joohong Lee, Juhyun Oh, Sungwon Ryu, Younghoon Jeong, Inkwon Lee, Sangwoo Seo, Dongjun Lee, Hyunwoo Kim, Myeonghwa Lee, Seongbo Jang, Seungwon Do, Sunkyoung Kim, Kyungtae Lim, Jongwon Lee, Kyumin Park, Jamin Shin, Seonghyun Kim, Lucy Park, Alice Oh, Jung-Woo Ha, Kyunghyun Cho"
|
2291 |
},
|
2292 |
{
|
2293 |
-
"name":"Explosion
|
2294 |
"url":"https://github.com/explosion/spacy-vectors-builder",
|
2295 |
"license":"CC0",
|
2296 |
"author":"Explosion"
|
|
|
1 |
{
|
2 |
"lang":"ko",
|
3 |
"name":"core_news_md",
|
4 |
+
"version":"3.4.0",
|
5 |
"description":"Korean pipeline optimized for CPU. Components: tok2vec, tagger, morphologizer, parser, lemmatizer (trainable_lemmatizer), senter, ner.",
|
6 |
"author":"Explosion",
|
7 |
"email":"contact@explosion.ai",
|
8 |
"url":"https://explosion.ai",
|
9 |
"license":"CC BY-SA 4.0",
|
10 |
+
"spacy_version":">=3.4.0,<3.5.0",
|
11 |
+
"spacy_git_version":"dd038b536",
|
12 |
"vectors":{
|
13 |
"width":300,
|
14 |
"vectors":50000,
|
|
|
20 |
|
21 |
],
|
22 |
"tagger":[
|
23 |
+
"_SP",
|
24 |
"ecs",
|
25 |
"etm",
|
26 |
"f",
|
|
|
2006 |
"POS=VERB",
|
2007 |
"POS=ADJ",
|
2008 |
"POS=PUNCT",
|
2009 |
+
"POS=SPACE",
|
2010 |
"POS=AUX",
|
2011 |
"POS=PRON",
|
2012 |
"POS=PROPN",
|
|
|
2086 |
"token_p":1.0,
|
2087 |
"token_r":1.0,
|
2088 |
"token_f":1.0,
|
2089 |
+
"tag_acc":0.8336399059,
|
2090 |
+
"pos_acc":0.946239962,
|
2091 |
+
"sents_p":0.998065764,
|
2092 |
+
"sents_r":0.9990319458,
|
2093 |
+
"sents_f":0.9985486212,
|
2094 |
+
"dep_uas":0.83875855,
|
2095 |
+
"dep_las":0.8092235713,
|
2096 |
"dep_las_per_type":{
|
2097 |
"amod":{
|
2098 |
+
"p":0.8202443281,
|
2099 |
+
"r":0.823117338,
|
2100 |
+
"f":0.8216783217
|
2101 |
},
|
2102 |
"dislocated":{
|
2103 |
+
"p":0.7434725849,
|
2104 |
+
"r":0.7405721717,
|
2105 |
+
"f":0.742019544
|
2106 |
},
|
2107 |
"root":{
|
2108 |
+
"p":0.8689555126,
|
2109 |
+
"r":0.8697967086,
|
2110 |
+
"f":0.8693759071
|
2111 |
},
|
2112 |
"nmod":{
|
2113 |
+
"p":0.8883610451,
|
2114 |
+
"r":0.8878338279,
|
2115 |
+
"f":0.8880973583
|
2116 |
},
|
2117 |
"nsubj":{
|
2118 |
+
"p":0.7961089494,
|
2119 |
+
"r":0.8157894737,
|
2120 |
+
"f":0.8058290666
|
2121 |
},
|
2122 |
"advmod":{
|
2123 |
+
"p":0.7191097467,
|
2124 |
+
"r":0.7354788069,
|
2125 |
+
"f":0.7272021731
|
2126 |
},
|
2127 |
"dep":{
|
2128 |
+
"p":0.6642335766,
|
2129 |
+
"r":0.5027624309,
|
2130 |
+
"f":0.572327044
|
2131 |
},
|
2132 |
"conj":{
|
2133 |
+
"p":0.7157057654,
|
2134 |
+
"r":0.6923076923,
|
2135 |
+
"f":0.7038123167
|
2136 |
},
|
2137 |
"xcomp":{
|
2138 |
+
"p":0.6344827586,
|
2139 |
+
"r":0.6323024055,
|
2140 |
+
"f":0.6333907057
|
2141 |
},
|
2142 |
"flat":{
|
2143 |
+
"p":0.625,
|
2144 |
+
"r":0.1869158879,
|
2145 |
+
"f":0.2877697842
|
2146 |
},
|
2147 |
"obj":{
|
2148 |
+
"p":0.9232832618,
|
2149 |
+
"r":0.9247716282,
|
2150 |
+
"f":0.9240268456
|
2151 |
},
|
2152 |
"acl":{
|
2153 |
+
"p":0.8018072289,
|
2154 |
+
"r":0.7984403119,
|
2155 |
+
"f":0.8001202284
|
2156 |
},
|
2157 |
"advcl":{
|
2158 |
+
"p":0.7902571042,
|
2159 |
+
"r":0.7929395791,
|
2160 |
+
"f":0.7915960691
|
2161 |
},
|
2162 |
"det":{
|
2163 |
+
"p":0.7652733119,
|
2164 |
+
"r":0.8947368421,
|
2165 |
+
"f":0.8249566724
|
2166 |
},
|
2167 |
"compound":{
|
2168 |
+
"p":0.7985823981,
|
2169 |
+
"r":0.8253968254,
|
2170 |
+
"f":0.8117682378
|
2171 |
},
|
2172 |
"ccomp":{
|
2173 |
+
"p":0.6488925349,
|
2174 |
+
"r":0.6564315353,
|
2175 |
+
"f":0.652640264
|
2176 |
},
|
2177 |
"obl":{
|
2178 |
+
"p":0.8827493261,
|
2179 |
+
"r":0.8935879945,
|
2180 |
+
"f":0.8881355932
|
2181 |
},
|
2182 |
"aux":{
|
2183 |
+
"p":0.9286713287,
|
2184 |
+
"r":0.9312762973,
|
2185 |
+
"f":0.9299719888
|
2186 |
},
|
2187 |
"cc":{
|
2188 |
+
"p":0.8193548387,
|
2189 |
+
"r":0.8410596026,
|
2190 |
+
"f":0.8300653595
|
2191 |
},
|
2192 |
"nummod":{
|
2193 |
+
"p":0.8540540541,
|
2194 |
+
"r":0.8272251309,
|
2195 |
+
"f":0.8404255319
|
2196 |
},
|
2197 |
"discourse":{
|
2198 |
"p":0.0,
|
|
|
2200 |
"f":0.0
|
2201 |
},
|
2202 |
"fixed":{
|
2203 |
+
"p":0.956,
|
2204 |
+
"r":1.0,
|
2205 |
+
"f":0.9775051125
|
2206 |
},
|
2207 |
"csubj":{
|
2208 |
+
"p":0.5393258427,
|
2209 |
+
"r":0.4363636364,
|
2210 |
+
"f":0.4824120603
|
2211 |
},
|
2212 |
"mark":{
|
2213 |
+
"p":0.6923076923,
|
2214 |
+
"r":0.5538461538,
|
2215 |
+
"f":0.6153846154
|
2216 |
},
|
2217 |
"iobj":{
|
2218 |
+
"p":0.8169014085,
|
2219 |
+
"r":0.8169014085,
|
2220 |
+
"f":0.8169014085
|
2221 |
},
|
2222 |
"case":{
|
2223 |
+
"p":0.8260869565,
|
2224 |
+
"r":0.8382352941,
|
2225 |
+
"f":0.8321167883
|
2226 |
},
|
2227 |
"cop":{
|
2228 |
+
"p":0.6666666667,
|
2229 |
+
"r":0.6666666667,
|
2230 |
+
"f":0.6666666667
|
2231 |
},
|
2232 |
"vocative":{
|
2233 |
"p":0.0,
|
|
|
2235 |
"f":0.0
|
2236 |
},
|
2237 |
"appos":{
|
2238 |
+
"p":0.7142857143,
|
2239 |
"r":0.7142857143,
|
2240 |
+
"f":0.7142857143
|
2241 |
}
|
2242 |
},
|
2243 |
+
"lemma_acc":0.8970905279,
|
2244 |
+
"speed":5125.497744352,
|
2245 |
+
"ents_p":0.8490038962,
|
2246 |
+
"ents_r":0.8158954433,
|
2247 |
+
"ents_f":0.8321204698,
|
2248 |
"ents_per_type":{
|
2249 |
"OG":{
|
2250 |
+
"p":0.7671443193,
|
2251 |
+
"r":0.6949466852,
|
2252 |
+
"f":0.7292629531
|
2253 |
},
|
2254 |
"PS":{
|
2255 |
+
"p":0.859375,
|
2256 |
+
"r":0.7998182231,
|
2257 |
+
"f":0.8285277157
|
2258 |
},
|
2259 |
"QT":{
|
2260 |
+
"p":0.9160861305,
|
2261 |
+
"r":0.9275408785,
|
2262 |
+
"f":0.9217779194
|
2263 |
},
|
2264 |
"DT":{
|
2265 |
+
"p":0.8884462151,
|
2266 |
+
"r":0.8699609883,
|
2267 |
+
"f":0.8791064389
|
2268 |
},
|
2269 |
"LC":{
|
2270 |
+
"p":0.7082294264,
|
2271 |
+
"r":0.6986469865,
|
2272 |
+
"f":0.7034055728
|
2273 |
},
|
2274 |
"TI":{
|
2275 |
+
"p":0.9285714286,
|
2276 |
+
"r":0.9064220183,
|
2277 |
+
"f":0.9173630455
|
2278 |
}
|
2279 |
}
|
2280 |
},
|
|
|
2292 |
"author":"Sungjoon Park, Jihyung Moon, Sungdong Kim, Won Ik Cho, Jiyoon Han, Jangwon Park, Chisung Song, Junseong Kim, Youngsook Song, Taehwan Oh, Joohong Lee, Juhyun Oh, Sungwon Ryu, Younghoon Jeong, Inkwon Lee, Sangwoo Seo, Dongjun Lee, Hyunwoo Kim, Myeonghwa Lee, Seongbo Jang, Seungwon Do, Sunkyoung Kim, Kyungtae Lim, Jongwon Lee, Kyumin Park, Jamin Shin, Seonghyun Kim, Lucy Park, Alice Oh, Jung-Woo Ha, Kyunghyun Cho"
|
2293 |
},
|
2294 |
{
|
2295 |
+
"name":"Explosion Vectors (OSCAR 2109 + Wikipedia + OpenSubtitles + WMT News Crawl)",
|
2296 |
"url":"https://github.com/explosion/spacy-vectors-builder",
|
2297 |
"license":"CC0",
|
2298 |
"author":"Explosion"
|
morphologizer/cfg
CHANGED
@@ -9,6 +9,7 @@
|
|
9 |
"POS=VERB":"",
|
10 |
"POS=ADJ":"",
|
11 |
"POS=PUNCT":"",
|
|
|
12 |
"POS=AUX":"",
|
13 |
"POS=PRON":"",
|
14 |
"POS=PROPN":"",
|
@@ -28,6 +29,7 @@
|
|
28 |
"POS=VERB":100,
|
29 |
"POS=ADJ":84,
|
30 |
"POS=PUNCT":97,
|
|
|
31 |
"POS=AUX":87,
|
32 |
"POS=PRON":95,
|
33 |
"POS=PROPN":96,
|
|
|
9 |
"POS=VERB":"",
|
10 |
"POS=ADJ":"",
|
11 |
"POS=PUNCT":"",
|
12 |
+
"POS=SPACE":"",
|
13 |
"POS=AUX":"",
|
14 |
"POS=PRON":"",
|
15 |
"POS=PROPN":"",
|
|
|
29 |
"POS=VERB":100,
|
30 |
"POS=ADJ":84,
|
31 |
"POS=PUNCT":97,
|
32 |
+
"POS=SPACE":103,
|
33 |
"POS=AUX":87,
|
34 |
"POS=PRON":95,
|
35 |
"POS=PROPN":96,
|
morphologizer/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f20366c12c4f0c5f7cf7451500b669897b71f7b2e12cfb2e52efcd89a4acdfd
|
3 |
+
size 7413
|
ner/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6498672
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2898e2dc21075fd89f19e3dfe5a71950b02d1a0923ef3811dcd486d7fed76938
|
3 |
size 6498672
|
ner/moves
CHANGED
@@ -1 +1 @@
|
|
1 |
-
��moves�,{"0":{},"1":{"PS":
|
|
|
1 |
+
��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
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 305088
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d503264583f74dad9660b68b8520590a98018d588a90f8a5bbf5e32b1ac8c87
|
3 |
size 305088
|
parser/moves
CHANGED
@@ -1 +1 @@
|
|
1 |
-
��moves��{"0":{"":
|
|
|
1 |
+
��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
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 219953
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:866dcfd531f5295c04fdbe3c1530253ad2ced34da3f8b72a5f1fa7e910fa9849
|
3 |
size 219953
|
tagger/cfg
CHANGED
@@ -1,5 +1,6 @@
|
|
1 |
{
|
2 |
"labels":[
|
|
|
3 |
"ecs",
|
4 |
"etm",
|
5 |
"f",
|
|
|
1 |
{
|
2 |
"labels":[
|
3 |
+
"_SP",
|
4 |
"ecs",
|
5 |
"etm",
|
6 |
"f",
|
tagger/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:30eb986406370bc15c5ac2aa36a69283e65f5da92b608a7533f5e58fc2b2cabe
|
3 |
+
size 767130
|
tok2vec/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6365604
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1de95f6c5dcc381c5cb1a5c50b1840c1c4bc1a06a3a3a5a9bcbb75fa806490e
|
3 |
size 6365604
|
vocab/strings.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6629d48d9e2b106d9424c6dc70e5979416c14410ee42e8d42f7f3234f9229f35
|
3 |
+
size 9944642
|