|
--- |
|
tags: |
|
- spacy |
|
- token-classification |
|
language: |
|
- nl |
|
model-index: |
|
- name: nl_pipeline |
|
results: |
|
- task: |
|
name: NER |
|
type: token-classification |
|
metrics: |
|
- name: NER Precision |
|
type: precision |
|
value: 0.6350364964 |
|
- name: NER Recall |
|
type: recall |
|
value: 0.5878378378 |
|
- name: NER F Score |
|
type: f_score |
|
value: 0.6105263158 |
|
--- |
|
| Feature | Description | |
|
| --- | --- | |
|
| **Name** | `nl_pipeline` | |
|
| **Version** | `0.0.0` | |
|
| **spaCy** | `>=3.6.1,<3.7.0` | |
|
| **Default Pipeline** | `tok2vec`, `ner` | |
|
| **Components** | `tok2vec`, `ner` | |
|
| **Vectors** | 0 keys, 0 unique vectors (0 dimensions) | |
|
| **Sources** | n/a | |
|
| **License** | n/a | |
|
| **Author** | [n/a]() | |
|
|
|
### Label Scheme |
|
|
|
<details> |
|
|
|
<summary>View label scheme (7 labels for 1 components)</summary> |
|
|
|
| Component | Labels | |
|
| --- | --- | |
|
| **`ner`** | `BEDRAG`, `LOC`, `ORG`, `PERSOON`, `PROJECT`, `SUB`, `TIJD` | |
|
|
|
</details> |
|
|
|
### Accuracy |
|
|
|
| Type | Score | |
|
| --- | --- | |
|
| `ENTS_F` | 61.05 | |
|
| `ENTS_P` | 63.50 | |
|
| `ENTS_R` | 58.78 | |
|
| `TOK2VEC_LOSS` | 41795.01 | |
|
| `NER_LOSS` | 26551.93 | |
|
|
|
### Description |
|
|
|
Voor meer info: https://github.com/RaThorat/my-chatbot-project |
|
|
|
Prodigy (ner.manual) is gebruikt om te annoteren van entiteiten zoals: PERSOON, ORGANISATIE, PROJECT, BEDRAG, LOCATIE, TIJDSPERIODE, SUBSIDIE, PRODUCT. |
|
|
|
<Annotatie> prodigy ner.manual ner_dataset nl_core_news_lg ./Data/combined_documents.txt --label PERSOON,ORG,PROJECT,BEDRAG,LOC,TIJD,SUB |
|
|
|
<Training> prodigy train ./models --ner ner_dataset --lang nl --label-stats --verbose --eval-split 0.2 |
|
|
|
<data>30 documenten (https://github.com/RaThorat/my-chatbot-project/tree/main/Data/txt) uit de DUS-i website gedownload, schoongemaakt, samengesteld in combined_documents.txt |