> 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-pos.md).

# SparkNLP POS

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

SparkNLP Part-of-Speech (POS) Tagging is a fast and scalable component of the SparkNLP library that assigns grammatical tags such as noun, verb, adjective, or adverb to each word in a sentence. It uses advanced NLP models optimized for large-scale processing, making it suitable for handling massive datasets efficiently. In our labeling platform, SparkNLP POS tagging enhances text analysis by providing syntactic insights that can improve label suggestions, rule-based automation, and overall annotation quality.

<figure><img src="/files/GyQVZl6sAkOePdazZKAr" alt="Image of ML Assisted with SparkNLP POS"><figcaption></figcaption></figure>

### Model details

* POS-tagging in SparkNLP is done via the `en.pos` model from [johnsnowlabs/nlp\_server](https://nlp.johnsnowlabs.com/docs/en/nlp_server/nlp_server).
* Models are trained primarily on the Penn Treebank corpus, supplemented with diverse web content to improve robustness across text types.
* Operates as a service accessible within the Datasaur Intelligence container.

### Usage

* SparkNLP POS tagging is ideal for large-scale text processing, including syntactic analysis and document parsing.
* The tagset is similar to the [NLTK](/assisted-labeling/ml-assisted-labeling/nltk.md#treebank-tagset) provider.

### References

* <https://nlp.johnsnowlabs.com/docs/en/nlp_server/nlp_server>
* <https://nlu.johnsnowlabs.com/docs/en/examples#part-of-speech--pos>