Token Classification
spaCy
Danish
dacy
danish
pos tagging
morphological analysis
lemmatization
dependency parsing
named entity recognition
coreference resolution
named entity linking
named entity disambiguation
Eval Results (legacy)
Instructions to use chcaa/da_dacy_medium_trf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- spaCy
How to use chcaa/da_dacy_medium_trf with spaCy:
!pip install https://huggingface.co/chcaa/da_dacy_medium_trf/resolve/main/da_dacy_medium_trf-any-py3-none-any.whl # Using spacy.load(). import spacy nlp = spacy.load("da_dacy_medium_trf") # Importing as module. import da_dacy_medium_trf nlp = da_dacy_medium_trf.load() - Notebooks
- Google Colab
- Kaggle
Kenneth Enevoldsen commited on
Commit ·
9ebd830
1
Parent(s): 2ea5d62
Added datasets
Browse files
README.md
CHANGED
|
@@ -21,6 +21,10 @@ model-index:
|
|
| 21 |
- name: NER F Score
|
| 22 |
type: f_score
|
| 23 |
value: 0.8581818182
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
- task:
|
| 25 |
name: TAG
|
| 26 |
type: token-classification
|
|
@@ -28,6 +32,9 @@ model-index:
|
|
| 28 |
- name: TAG (XPOS) Accuracy
|
| 29 |
type: accuracy
|
| 30 |
value: 0.9847290149
|
|
|
|
|
|
|
|
|
|
| 31 |
- task:
|
| 32 |
name: POS
|
| 33 |
type: token-classification
|
|
@@ -35,6 +42,9 @@ model-index:
|
|
| 35 |
- name: POS (UPOS) Accuracy
|
| 36 |
type: accuracy
|
| 37 |
value: 0.985677928
|
|
|
|
|
|
|
|
|
|
| 38 |
- task:
|
| 39 |
name: MORPH
|
| 40 |
type: token-classification
|
|
@@ -42,6 +52,9 @@ model-index:
|
|
| 42 |
- name: Morph (UFeats) Accuracy
|
| 43 |
type: accuracy
|
| 44 |
value: 0.9814371257
|
|
|
|
|
|
|
|
|
|
| 45 |
- task:
|
| 46 |
name: UNLABELED_DEPENDENCIES
|
| 47 |
type: token-classification
|
|
@@ -49,6 +62,9 @@ model-index:
|
|
| 49 |
- name: Unlabeled Attachment Score (UAS)
|
| 50 |
type: f_score
|
| 51 |
value: 0.9083920564
|
|
|
|
|
|
|
|
|
|
| 52 |
- task:
|
| 53 |
name: LABELED_DEPENDENCIES
|
| 54 |
type: token-classification
|
|
@@ -56,6 +72,9 @@ model-index:
|
|
| 56 |
- name: Labeled Attachment Score (LAS)
|
| 57 |
type: f_score
|
| 58 |
value: 0.883349834
|
|
|
|
|
|
|
|
|
|
| 59 |
- task:
|
| 60 |
name: SENTS
|
| 61 |
type: token-classification
|
|
@@ -63,9 +82,41 @@ model-index:
|
|
| 63 |
- name: Sentences F-Score
|
| 64 |
type: f_score
|
| 65 |
value: 0.9885462555
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 66 |
---
|
| 67 |
|
| 68 |
|
|
|
|
| 69 |
<a href="https://github.com/centre-for-humanities-computing/Dacy"><img src="https://centre-for-humanities-computing.github.io/DaCy/_static/icon.png" width="175" height="175" align="right" /></a>
|
| 70 |
|
| 71 |
# DaCy medium
|
|
|
|
| 21 |
- name: NER F Score
|
| 22 |
type: f_score
|
| 23 |
value: 0.8581818182
|
| 24 |
+
dataset:
|
| 25 |
+
name: DaNE
|
| 26 |
+
split: test
|
| 27 |
+
type: dane
|
| 28 |
- task:
|
| 29 |
name: TAG
|
| 30 |
type: token-classification
|
|
|
|
| 32 |
- name: TAG (XPOS) Accuracy
|
| 33 |
type: accuracy
|
| 34 |
value: 0.9847290149
|
| 35 |
+
dataset:
|
| 36 |
+
name: UD Danish DDT
|
| 37 |
+
split: test
|
| 38 |
- task:
|
| 39 |
name: POS
|
| 40 |
type: token-classification
|
|
|
|
| 42 |
- name: POS (UPOS) Accuracy
|
| 43 |
type: accuracy
|
| 44 |
value: 0.985677928
|
| 45 |
+
dataset:
|
| 46 |
+
name: UD Danish DDT
|
| 47 |
+
split: test
|
| 48 |
- task:
|
| 49 |
name: MORPH
|
| 50 |
type: token-classification
|
|
|
|
| 52 |
- name: Morph (UFeats) Accuracy
|
| 53 |
type: accuracy
|
| 54 |
value: 0.9814371257
|
| 55 |
+
dataset:
|
| 56 |
+
name: UD Danish DDT
|
| 57 |
+
split: test
|
| 58 |
- task:
|
| 59 |
name: UNLABELED_DEPENDENCIES
|
| 60 |
type: token-classification
|
|
|
|
| 62 |
- name: Unlabeled Attachment Score (UAS)
|
| 63 |
type: f_score
|
| 64 |
value: 0.9083920564
|
| 65 |
+
dataset:
|
| 66 |
+
name: UD Danish DDT
|
| 67 |
+
split: test
|
| 68 |
- task:
|
| 69 |
name: LABELED_DEPENDENCIES
|
| 70 |
type: token-classification
|
|
|
|
| 72 |
- name: Labeled Attachment Score (LAS)
|
| 73 |
type: f_score
|
| 74 |
value: 0.883349834
|
| 75 |
+
dataset:
|
| 76 |
+
name: UD Danish DDT
|
| 77 |
+
split: test
|
| 78 |
- task:
|
| 79 |
name: SENTS
|
| 80 |
type: token-classification
|
|
|
|
| 82 |
- name: Sentences F-Score
|
| 83 |
type: f_score
|
| 84 |
value: 0.9885462555
|
| 85 |
+
dataset:
|
| 86 |
+
name: UD Danish DDT
|
| 87 |
+
split: test
|
| 88 |
+
- task:
|
| 89 |
+
name: coreference-resolution
|
| 90 |
+
type: coreference-resolution
|
| 91 |
+
metrics:
|
| 92 |
+
- name: LEA
|
| 93 |
+
type: f_score
|
| 94 |
+
value: 0.4118366346
|
| 95 |
+
dataset:
|
| 96 |
+
name: DaCoref
|
| 97 |
+
type: alexandrainst/dacoref
|
| 98 |
+
split: custom
|
| 99 |
+
- task:
|
| 100 |
+
name: coreference-resolution
|
| 101 |
+
type: coreference-resolution
|
| 102 |
+
metrics:
|
| 103 |
+
- name: Named entity Linking Precision
|
| 104 |
+
type: precision
|
| 105 |
+
value: 0.9923076923
|
| 106 |
+
- name: Named entity Linking Recall
|
| 107 |
+
type: recall
|
| 108 |
+
value: 0.671875
|
| 109 |
+
- name: Named entity Linking F Score
|
| 110 |
+
type: f_score
|
| 111 |
+
value: 0.801242236
|
| 112 |
+
dataset:
|
| 113 |
+
name: DaNED
|
| 114 |
+
type: named-entity-linking
|
| 115 |
+
split: custom
|
| 116 |
---
|
| 117 |
|
| 118 |
|
| 119 |
+
|
| 120 |
<a href="https://github.com/centre-for-humanities-computing/Dacy"><img src="https://centre-for-humanities-computing.github.io/DaCy/_static/icon.png" width="175" height="175" align="right" /></a>
|
| 121 |
|
| 122 |
# DaCy medium
|