docs: extend tutorial14 about query classification

[anakin87]

As stated in #2965, it would be good to include in Tutorial 14 a small section about new features of TransformersQueryClassifier:

• using custom transformer models
• using zero-shot-classification

Proposed Changes:

I added a small section on these features, similar to what has been done for the features already present.
I'm not that good with documentation, so I'd beg the people involved (@agnieszka-m @TuanaCelik @mkkuemmel) to brutally make the necessary changes 😃

Checklist

• I have read the contributors guidelines and the code of conduct
• I have updated the related issue with new insights and changes
• I added tests that demonstrate the correct behavior of the change
• I've used the conventional commit convention for my PR title
• I documented my code
• I ran pre-commit hooks and fixed any issue

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[TuanaCelik]

@agnieszka-m, looping you in here as I think you'd like to have a look at the language. @anakin87 I'll also put in a review 🙂

[TuanaCelik]

Overall I think this is great. I would have one suggestion though, as it's a tutorial, I think it might be useful to be a bit more explicit about the difference of zero-shot vs custom classification. The reader might not understand the difference in the current version. For example it starts off with how for custom, you can use a model from the hub. But then you see that you can also use one for zero-shot. The other thing is they might not understand the difference of you defining your own labels like 'cinema' and 'music' being any different to the other labels which are simply 'label1' etc.

All in all some more hand holding go well for a tutorial 👍🏽

Thank you for the contribution!! 🎉

[agnieszka-m]

Hi! Since my changes are mostly minor language corrections, would you like me to do them directly on your files or would you rather I add comments to the files? Whatever works best for you.

[anakin87]

@TuanaCelik I made some improvements. Please let me know WDYT... 😃

Hi! Since my changes are mostly minor language corrections, would you like me to do them directly on your files or would you rather I add comments to the files? Whatever works best for you.

@agnieszka-m for me it is the same...

[agnieszka-m]

Added my two cents.

[anakin87]

When the notebook tutorial is acceptable, I will add the .py version as well.

[tstadel]

I like it very much, nice examples.
Btw, we're planning to make zero-shot query classification one of the highlights of our next release (probably monday). So it would be awesome to have this PR.

[TuanaCelik]

Looks good to me! Thanks @anakin87

[anakin87]

I've made some minor fixes and added the .py tutorial.
In the next few days, I won't be online ⛱️, so feel free to make corrections (if needed) and take charge of this PR.

[agnieszka-m]

Minor lg corrections

[tstadel]

@anakin87 this is almost good to go. Only the tutorial script is missing. I'm pushing it over the finish line.

[tstadel]

@anakin87 unfortunately I don't have write access. Can you run the script yourself or grant me access?

[anakin87]

'Allow edits and access to secrets by maintainers' is already selected. What can I do to allow you?

[tstadel]

'Allow edits and access to secrets by maintainers' is already selected. What can I do to allow you?

@anakin87 Ok, weird. To fix this quickly, can you grant me access individually maybe?

[anakin87]

I invited you to collaborate on my fork... Hope it helps...

[tstadel]

@anakin87 Yes thanks! Now it's working.