# Country code classification

**URL:** <https://discuss.huggingface.co/t/country-code-classification/90754>\
**Category:** Models\
**Created:** [June 6, 2024, 8:27pm UTC](https://discuss.huggingface.co/t/country-code-classification/90754 "2024-06-06T20:27:02Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Abasov](https://avatars.discourse-cdn.com/v4/letter/a/35a633/32.png) [@Abasov](https://discuss.huggingface.co/u/Abasov)\
**Post date:** [June 6, 2024, 8:27pm UTC](https://discuss.huggingface.co/t/country-code-classification/90754/1 "2024-06-06T20:27:02Z")

</div>

Hello everyone!

I have a dataset with country names. Like Russian, United states, and etc. But these data is very dirty, not always come in english. My goal is to classify these country names to country codes, so russian will be ru, England to GB and etc. Whats your NLP model approach suggestion for such a dataset? Note that, again, dataset come in different languages, mainly in azerbaijani. The labels should follow ISO 316 standards.

---

<div class="post-metadata">

**Author:** ![MattiLinnanvuori](https://avatars.discourse-cdn.com/v4/letter/m/ec9cab/32.png) [@MattiLinnanvuori](https://discuss.huggingface.co/u/MattiLinnanvuori)\
**Post date:** [June 8, 2024, 8:46am UTC](https://discuss.huggingface.co/t/country-code-classification/90754/2 "2024-06-08T08:46:43Z")

</div>

[[Text classification](https://huggingface.co/docs/transformers/tasks/sequence_classification)] Hugging Face has a page called Text classification that can be used for country code classification. You can research and test different multilingual models.