metadata

tags:
  - spacy
  - token-classification
language:
  - en
model-index:
  - name: en_chemner
    results:
      - task:
          name: NER
          type: token-classification
        metrics:
          - name: NER Precision
            type: precision
            value: 0.9906542056
          - name: NER Recall
            type: recall
            value: 0.9636363636
          - name: NER F Score
            type: f_score
            value: 0.9769585253
widget:
  - text: >-
      Cinammaldehyde is a fragrant compound found in cinammon. Icosanoic acid,
      is a saturated fatty acid with a 20-carbon chain. Triptane is commonly
      used as an anti-knock additive in aviation fuels. Benzophenone is a widely
      used building block in organic chemistry, being the parent diarylketone.
      Geraniol is a monoterpenoid and an alcohol. It is the primary component of
      citronella oil and is a primary component of rose oil, palmarosa oil.
license: apache-2.0

en_chemner: A spaCy Model for Chemical NER

Model Description

The en_chemner model is a specialized Named Entity Recognition (NER) tool designed for the field of chemistry. Built using the spaCy framework, it identifies and classifies chemical entities within English-language texts.

Key Features

High Precision and Recall: With a precision of 99.07% and a recall of 96.36%, the model offers highly accurate entity recognition, minimizing both false positives and false negatives.
Rich Label Scheme: The model can identify a variety of chemical entities such as alcohols, aldehydes, alkanes, and more, making it versatile for different chemical analysis tasks.
Optimized for spaCy: Integrated seamlessly with spaCy (>=3.6.1,<3.7.0), allowing for easy incorporation into existing spaCy pipelines and applications.
Extensive Vector Library: Comes with over 514,000 unique vectors, each with 300 dimensions, providing a rich foundation for understanding and classifying chemical entities.

Use Cases

The `en_chemner` model is ideal for: - Chemical Literature Analysis: Automatically extracting chemical entities from research papers, patents, and textbooks. - Data Annotation: Assisting in the annotation of chemical databases or creating datasets for further machine learning tasks. - Educational Purposes: Helping students in chemistry-related fields to identify and understand various chemical compounds and their classifications.

Feature	Description
Name	`en_chemner`
Version	`1.0.0`
spaCy	`>=3.6.1,<3.7.0`
Default Pipeline	`tok2vec`, `ner`
Components	`tok2vec`, `ner`
Vectors	514157 keys, 514157 unique vectors (300 dimensions)
Sources	n/a
License	n/a
Author	n/a

Label Scheme

View label scheme (7 labels for 1 components)

Component	Labels
`ner`	`ALCOHOL`, `ALDEHYDE`, `ALKANE`, `ALKENE`, `ALKYNE`, `C_ACID`, `KETONE`

Accuracy

Type	Score
`ENTS_F`	97.70
`ENTS_P`	99.07
`ENTS_R`	96.36
`TOK2VEC_LOSS`	151.95
`NER_LOSS`	259.22