# Create tags / keywords from text

**URL:** <https://discuss.huggingface.co/t/create-tags-keywords-from-text/16408>\
**Category:** Beginners\
**Created:** [April 3, 2022, 8:19am UTC](https://discuss.huggingface.co/t/create-tags-keywords-from-text/16408 "2022-04-03T08:19:06Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![caruso33](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/caruso33/32/4416_2.png) [@caruso33](https://discuss.huggingface.co/u/caruso33)\
**Post date:** [April 3, 2022, 8:19am UTC](https://discuss.huggingface.co/t/create-tags-keywords-from-text/16408/1 "2022-04-03T08:19:06Z")

</div>

Hi there,

I am trying to figuring out if it’s possible to implement the functionality with huggingface to create tags of a corpus for each individual text.

E.g. I have a corpus with AI related news and the model will be able to categorize the single articles into “NLP”, “Vision”, etc. where it comes up with the tags by itself and the number of tags are dynamic depending on the content.

Is this feasible somehow?

Thanks in advance,  
best

Tobias

---

<div class="post-metadata">

**Author:** ![merve](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/merve/32/49809_2.png) [@merve](https://discuss.huggingface.co/u/merve)\
**Post date:** [April 4, 2022, 10:46am UTC](https://discuss.huggingface.co/t/create-tags-keywords-from-text/16408/2 "2022-04-04T10:46:35Z")

</div>

Hello,

I feel like what you’re looking for is [zero shot classification](https://huggingface.co/facebook/bart-large-mnli) for the number of tags that are dynamic depending on the content, or multi-label text classification. Another thing you can do is to fine-tune BERT for multi-label text classification if you already have annotated data.

---

<div class="post-metadata">

**Author:** ![rubberfruit](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/rubberfruit/32/50563_2.png) [@rubberfruit](https://discuss.huggingface.co/u/rubberfruit)\
**Post date:** [July 3, 2025, 9:03am UTC](https://discuss.huggingface.co/t/create-tags-keywords-from-text/16408/3 "2025-07-03T09:03:31Z")

</div>

i am working on the user preference tagging

 ![image](https://us1.discourse-cdn.com/hellohellohello/original/3X/4/e/4e01786ecdc3faeb285da9ae6a9b6821f27550d4.png)  
from the image i need to complete the task one without any mis matching and precise output

---

<div class="post-metadata">

**Author:** ![John6666](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/john6666/32/27664_2.png) [@John6666](https://discuss.huggingface.co/u/John6666)\
**Post date:** [July 3, 2025, 10:22am UTC](https://discuss.huggingface.co/t/create-tags-keywords-from-text/16408/4 "2025-07-03T10:22:39Z")

</div>

Hmm…?

> **[Zero-Shot Text Classification using HuggingFace Model - GeeksforGeeks](https://www.geeksforgeeks.org/nlp/zero-shot-text-classification-using-huggingface-model/)**
>
> Your All-in-One Learning Portal: GeeksforGeeks is a comprehensive educational platform that empowers learners across domains-spanning computer science and programming, school education, upskilling, commerce, software tools, competitive exams, and...

> **[Multi-Label Classification Model From Scratch: Step-by-Step Tutorial](https://huggingface.co/blog/Valerii-Knowledgator/multi-label-classification)**
>
> A Blog post by Valerii Vasylevskyi on Hugging Face