How do I go about solving this? The category descriptions are made up of sentences and multiple list. The input description is a paragraph. I looked at zero-shot classification but the labels are only one word description - how do I handle multiple words/sentence?
Input = “an application that convert speech to text using AI”
Desired Output: category 1 match = 0.1 category 2 match = 0.9 …
Category 1 description = “medical equipment includes wearable devices”
Category 2 description =“software for SaaS or downloadable”
…
In order words I am trying to ask hugging face to learn the description of various categories that are in sentences or item list.
Then I am asking hugging face to classify a paragraph description input to see which of the categories best matched this description.