Update README.md
Browse files
README.md
CHANGED
|
@@ -77,36 +77,37 @@ pipeline_tag: token-classification
|
|
| 77 |
|
| 78 |
# Information extraction from Resumes/CVs written in English
|
| 79 |
|
| 80 |
-
|
| 81 |
-
|
| 82 |
-
| **Name** | `en_cv_info_extr` |
|
| 83 |
-
| **Version** | `0.0.0` |
|
| 84 |
-
| **spaCy** | `>=3.6.1,<3.7.0` |
|
| 85 |
-
| **Default Pipeline** | `transformer`, `ner` |
|
| 86 |
-
| **Components** | `transformer`, `ner` |
|
| 87 |
-
| **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
|
| 88 |
-
| **Sources** | n/a |
|
| 89 |
-
| **License** | n/a |
|
| 90 |
-
| **Author** | [Youssef Chafiqui](https://huggingface.co/ychafiqui) |
|
| 91 |
-
|
| 92 |
-
### Label Scheme
|
| 93 |
|
| 94 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 95 |
|
| 96 |
-
|
| 97 |
-
|
| 98 |
-
| Component | Labels |
|
| 99 |
-
| --- | --- |
|
| 100 |
-
| **`ner`** | `ADDRESS`, `CERTIFICATION`, `EDUCATION`, `EMAIL`, `EXPERIENCE`, `FNAME`, `HOBBY`, `HSKILL`, `LANGUAGE`, `LNAME`, `PHONE`, `PROFILE`, `PROJECT`, `SSKILL` |
|
| 101 |
|
| 102 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 103 |
|
| 104 |
-
###
|
| 105 |
|
| 106 |
| Type | Score |
|
| 107 |
| --- | --- |
|
| 108 |
-
| `
|
| 109 |
-
| `
|
| 110 |
-
| `
|
| 111 |
-
| `TRANSFORMER_LOSS` | 1473.09 |
|
| 112 |
-
| `NER_LOSS` | 287784.88 |
|
|
|
|
| 77 |
|
| 78 |
# Information extraction from Resumes/CVs written in English
|
| 79 |
|
| 80 |
+
### Model Description
|
| 81 |
+
This model is designed for information extraction from resumes/CVs written in English. It employs a transformer-based architecture with spaCy for named entity recognition (NER) tasks. The model aims to parse various sections of resumes, including personal details, education history, professional experience, skills, and certifications, enabling users to extract structured information for further processing or analysis.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 82 |
|
| 83 |
+
### Model Details
|
| 84 |
+
**Language:** English
|
| 85 |
+
**Task:** Information extraction from resumes/CVs
|
| 86 |
+
**Components:** Transformer, Named Entity Recognition (NER)
|
| 87 |
+
**Author:** [Youssef Chafiqui](https://huggingface.co/ychafiqui)
|
| 88 |
|
| 89 |
+
### Labels
|
| 90 |
+
The model recognizes various labels corresponding to different sections of a resume. Below are some of the labels used by the model:
|
|
|
|
|
|
|
|
|
|
| 91 |
|
| 92 |
+
**ADDRESS:**
|
| 93 |
+
**CERTIFICATION:**
|
| 94 |
+
**EDUCATION:**
|
| 95 |
+
**EMAIL:**
|
| 96 |
+
**EXPERIENCE:**
|
| 97 |
+
**FNAME:**
|
| 98 |
+
**HOBBY:**
|
| 99 |
+
**HSKILL:**
|
| 100 |
+
**LANGUAGE:**
|
| 101 |
+
**LNAME:**
|
| 102 |
+
**PHONE:**
|
| 103 |
+
**PROFILE:**
|
| 104 |
+
**PROJECT:**
|
| 105 |
+
**SSKILL:**
|
| 106 |
|
| 107 |
+
### Evaluation Metrics
|
| 108 |
|
| 109 |
| Type | Score |
|
| 110 |
| --- | --- |
|
| 111 |
+
| `NER F1 score` | 81.98 |
|
| 112 |
+
| `NER Precision` | 83.33 |
|
| 113 |
+
| `NER Recall` | 80.68 |
|
|
|
|
|
|