> For the complete documentation index, see [llms.txt](https://docs.datasaur.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.datasaur.ai/assisted-labeling/ml-assisted-labeling/sparknlp-ner.md).

# SparkNLP NER

{% hint style="info" %}
**Supported labeling types**: Span labeling.
{% endhint %}

SparkNLP Named Entity Recognition (NER) is a high-performance, scalable NLP component built on Apache Spark. It supports deep learning-based NER models that can identify and classify entities such as names, locations, organizations, and dates in large volumes of text. SparkNLP NER enables fast and accurate entity suggestions, making it ideal for projects with large datasets or real-time processing needs. It also supports custom model training and multilingual NER, offering flexibility for various labeling tasks.

<figure><img src="/files/IIYGktOHavCDzAHPQzFX" alt="Image of ML Assisted with SparkNLP NER"><figcaption></figcaption></figure>

### Model details

* SparkNLP provides a deep learning-based NER system via [johnsnowlabs/nlp\_server](https://nlp.johnsnowlabs.com/docs/en/nlp_server/nlp_server).
* The pre-trained `en.ner` model is designed for entity recognition tasks.
* Models are trained on diverse sources including CoNLL 2003 (Reuters news), OntoNotes 5.0, and proprietary datasets curated by John Snow Labs.
* Operates as a service accessible within the Datasaur Intelligence container.

### Usage

* This is ideal for complex linguistic analysis and tasks requiring detailed syntactic structures.
* Tag set: `LOC`, `ORG`, `PER`, `MISC`.

### References

* <https://nlp.johnsnowlabs.com/docs/en/nlp_server/nlp_server>