xx_eb_ner / README.md
philipp-zettl's picture
Update README.md
f4ce594 verified
metadata
tags:
  - spacy
  - token-classification
language:
  - multilingual
widget:
  - text: I'm looking for courses in machine learning.
    example_title: Course example
  - text: Can you send me some sales jobs?
    example_title: Job example
  - text: I'm from Berlin, Germany. Can you recommend courses to me?
    example_title: Location example
  - text: >-
      Next month I will be moving to London. I'm looking for software
      development jobs there. And can you recommend any language courses so I
      can meet new people?
    example_title: Mixed example
model-index:
  - name: xx_eb_ner
    results:
      - task:
          name: NER
          type: token-classification
        metrics:
          - name: NER Precision
            type: precision
            value: 0.99471974
          - name: NER Recall
            type: recall
            value: 0.9937070263
          - name: NER F Score
            type: f_score
            value: 0.9942131253
license: mit
library_name: spacy
Feature Description
Name xx_eb_ner
Version 0.2.0
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 mit
Author philipp-zettl

Label Scheme

View label scheme (3 labels for 1 components)
Component Labels
ner COURSE_NAME, JOB_TITLE, LOCATION

Accuracy

Type Score
ENTS_F 99.54
ENTS_P 99.56
ENTS_R 99.52
TOK2VEC_LOSS 35345.94
NER_LOSS 32265.61

Usage

Install the model via pip:

pip install https://huggingface.co/philipp-zettl/xx_eb_ner/resolve/main/xx_eb_ner-any-py3-none-any.whl

For specific versions, please use the commits provided in the source repository. Example: version v0.2.0

pip install https://huggingface.co/philipp-zettl/xx_eb_ner/resolve/v0.2.0/xx_eb_ner-any-py3-none-any.whl

After installing the model with it's dependencies, you can use it like any other SpaCy model:

# Using spacy.load().
import spacy
nlp = spacy.load("xx_eb_ner")

# Importing as module.
import xx_eb_ner
nlp = xx_eb_ner.load()