Update README.md
Browse files
README.md
CHANGED
|
@@ -15,41 +15,21 @@ model-index:
|
|
| 15 |
metrics:
|
| 16 |
- name: NER Precision
|
| 17 |
type: precision
|
| 18 |
-
value: 0.
|
| 19 |
- name: NER Recall
|
| 20 |
type: recall
|
| 21 |
-
value: 0.
|
| 22 |
- name: NER F Score
|
| 23 |
type: f_score
|
| 24 |
-
value: 0.
|
| 25 |
- task:
|
| 26 |
name: TAG
|
| 27 |
type: token-classification
|
| 28 |
metrics:
|
| 29 |
- name: TAG (XPOS) Accuracy
|
| 30 |
type: accuracy
|
| 31 |
-
value: 0.
|
| 32 |
-
|
| 33 |
-
name: UNLABELED_DEPENDENCIES
|
| 34 |
-
type: token-classification
|
| 35 |
-
metrics:
|
| 36 |
-
- name: Unlabeled Attachment Score (UAS)
|
| 37 |
-
type: f_score
|
| 38 |
-
value: 0.9208198801
|
| 39 |
-
- task:
|
| 40 |
-
name: LABELED_DEPENDENCIES
|
| 41 |
-
type: token-classification
|
| 42 |
-
metrics:
|
| 43 |
-
- name: Labeled Attachment Score (LAS)
|
| 44 |
-
type: f_score
|
| 45 |
-
value: 0.9027174273
|
| 46 |
-
- task:
|
| 47 |
-
name: SENTS
|
| 48 |
-
type: token-classification
|
| 49 |
-
metrics:
|
| 50 |
-
- name: Sentences F-Score
|
| 51 |
-
type: f_score
|
| 52 |
-
value: 0.907098331
|
| 53 |
library_name: spacy
|
| 54 |
pipeline_tag: text-classification
|
| 55 |
---
|
|
@@ -82,7 +62,7 @@ import spacy
|
|
| 82 |
nlp = spacy.load("en_ner_job_postings")
|
| 83 |
|
| 84 |
# Process your text
|
| 85 |
-
text = "HR Specialist needed at
|
| 86 |
doc = nlp(text)
|
| 87 |
|
| 88 |
# Extract named entities
|
|
@@ -127,16 +107,7 @@ The model recognizes the following entity types:
|
|
| 127 |
|
| 128 |
| Type | Score |
|
| 129 |
| --- | --- |
|
| 130 |
-
| `
|
| 131 |
-
| `
|
| 132 |
-
| `
|
| 133 |
-
| `
|
| 134 |
-
| `TAG_ACC` | 97.35 |
|
| 135 |
-
| `SENTS_P` | 92.19 |
|
| 136 |
-
| `SENTS_R` | 89.27 |
|
| 137 |
-
| `SENTS_F` | 90.71 |
|
| 138 |
-
| `DEP_UAS` | 92.08 |
|
| 139 |
-
| `DEP_LAS` | 90.27 |
|
| 140 |
-
| `ENTS_P` | 85.16 |
|
| 141 |
-
| `ENTS_R` | 85.70 |
|
| 142 |
-
| `ENTS_F` | 85.43 |
|
|
|
|
| 15 |
metrics:
|
| 16 |
- name: NER Precision
|
| 17 |
type: precision
|
| 18 |
+
value: 0.7516398746
|
| 19 |
- name: NER Recall
|
| 20 |
type: recall
|
| 21 |
+
value: 0.6069711538
|
| 22 |
- name: NER F Score
|
| 23 |
type: f_score
|
| 24 |
+
value: 0.6742971968
|
| 25 |
- task:
|
| 26 |
name: TAG
|
| 27 |
type: token-classification
|
| 28 |
metrics:
|
| 29 |
- name: TAG (XPOS) Accuracy
|
| 30 |
type: accuracy
|
| 31 |
+
value: 0.7334810915
|
| 32 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
library_name: spacy
|
| 34 |
pipeline_tag: text-classification
|
| 35 |
---
|
|
|
|
| 62 |
nlp = spacy.load("en_ner_job_postings")
|
| 63 |
|
| 64 |
# Process your text
|
| 65 |
+
text = "HR Specialist needed at Google, Dallas, TX, with expertise in employee relations and a minimum of 4 years of HR experience."
|
| 66 |
doc = nlp(text)
|
| 67 |
|
| 68 |
# Extract named entities
|
|
|
|
| 107 |
|
| 108 |
| Type | Score |
|
| 109 |
| --- | --- |
|
| 110 |
+
| `TOKEN_P` | 75.57 |
|
| 111 |
+
| `TOKEN_R` | 60.58 |
|
| 112 |
+
| `TOKEN_F` | 67.57 |
|
| 113 |
+
| `CUSTOM_TAG_ACC` | 73.35 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|