update REAMDE
Browse files
README.md
CHANGED
@@ -40,16 +40,16 @@ This spaCy-based Named Entity Recognition (NER) model has been custom-trained to
|
|
40 |
|
41 |
### Key Features
|
42 |
Custom-trained for high accuracy in recognizing "profession," "facility," and "experience" entities.
|
43 |
-
Suitable for various
|
44 |
-
|
45 |
|
46 |
### Usage
|
47 |
#### Installation
|
48 |
##### You can install the custom spaCy NER model using pip:
|
49 |
|
50 |
```bash
|
51 |
-
|
52 |
-
|
53 |
```
|
54 |
#### Example Usage
|
55 |
Here's how you can use the model for entity recognition in Python:
|
@@ -59,7 +59,7 @@ Here's how you can use the model for entity recognition in Python:
|
|
59 |
import spacy
|
60 |
|
61 |
# Load the custom spaCy NER model
|
62 |
-
nlp = spacy.load("en_core_web_sm_job
|
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."
|
@@ -80,12 +80,13 @@ The model recognizes the following entity types:
|
|
80 |
|
81 |
| Feature | Description |
|
82 |
| --- | --- |
|
83 |
-
| **Name** | `en_core_web_sm_job
|
84 |
-
| **Version** | `3.
|
85 |
-
| **spaCy** | `>=3.
|
86 |
| **Default Pipeline** | `tok2vec`, `tagger`, `parser`, `attribute_ruler`, `lemmatizer`, `ner` |
|
87 |
| **Components** | `tok2vec`, `tagger`, `parser`, `senter`, `attribute_ruler`, `lemmatizer`, `ner` |
|
88 |
-
| **Vectors** |
|
|
|
89 |
| **License** | `MIT` |
|
90 |
|
91 |
|
@@ -107,7 +108,7 @@ The model recognizes the following entity types:
|
|
107 |
|
108 |
| Type | Score |
|
109 |
| --- | --- |
|
110 |
-
| `TOKEN_P` |
|
111 |
-
| `TOKEN_R` |
|
112 |
-
| `TOKEN_F` |
|
113 |
-
| `CUSTOM_TAG_ACC` |
|
|
|
40 |
|
41 |
### Key Features
|
42 |
Custom-trained for high accuracy in recognizing "profession," "facility," and "experience" entities.
|
43 |
+
Suitable for various professional info streams tasks, such as information extraction, content categorization, and more.
|
44 |
+
Currently Focus on the job seekers fields, can be easily integrated into your existing spaCy-based NLP pipelines.
|
45 |
|
46 |
### Usage
|
47 |
#### Installation
|
48 |
##### You can install the custom spaCy NER model using pip:
|
49 |
|
50 |
```bash
|
51 |
+
git lfs install
|
52 |
+
git clone https://huggingface.co/LPDoctor/en_core_web_sm_job_related
|
53 |
```
|
54 |
#### Example Usage
|
55 |
Here's how you can use the model for entity recognition in Python:
|
|
|
59 |
import spacy
|
60 |
|
61 |
# Load the custom spaCy NER model
|
62 |
+
nlp = spacy.load("en_core_web_sm_job")
|
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."
|
|
|
80 |
|
81 |
| Feature | Description |
|
82 |
| --- | --- |
|
83 |
+
| **Name** | `en_core_web_sm_job` |
|
84 |
+
| **Version** | `3.7.0` |
|
85 |
+
| **spaCy** | `>=3.7.0,<3.8.0` |
|
86 |
| **Default Pipeline** | `tok2vec`, `tagger`, `parser`, `attribute_ruler`, `lemmatizer`, `ner` |
|
87 |
| **Components** | `tok2vec`, `tagger`, `parser`, `senter`, `attribute_ruler`, `lemmatizer`, `ner` |
|
88 |
+
| **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
|
89 |
+
| **Sources** | [OntoNotes 5](https://catalog.ldc.upenn.edu/LDC2013T19) (Ralph Weischedel, Martha Palmer, Mitchell Marcus, Eduard Hovy, Sameer Pradhan, Lance Ramshaw, Nianwen Xue, Ann Taylor, Jeff Kaufman, Michelle Franchini, Mohammed El-Bachouti, Robert Belvin, Ann Houston)<br />[ClearNLP Constituent-to-Dependency Conversion](https://github.com/clir/clearnlp-guidelines/blob/master/md/components/dependency_conversion.md) (Emory University)<br />[WordNet 3.0](https://wordnet.princeton.edu/) (Princeton University) |
|
90 |
| **License** | `MIT` |
|
91 |
|
92 |
|
|
|
108 |
|
109 |
| Type | Score |
|
110 |
| --- | --- |
|
111 |
+
| `TOKEN_P` | 78.59 |
|
112 |
+
| `TOKEN_R` | 63.58 |
|
113 |
+
| `TOKEN_F` | 70.57 |
|
114 |
+
| `CUSTOM_TAG_ACC` | 71.98 |
|