# Zero-Shot Classification

**URL:** <https://discuss.huggingface.co/t/zero-shot-classification/18328>\
**Category:** 🤗Transformers\
**Created:** [May 24, 2022, 8:24pm UTC](https://discuss.huggingface.co/t/zero-shot-classification/18328 "2022-05-24T20:24:45Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![khanfarabi1234](https://avatars.discourse-cdn.com/v4/letter/k/b5ac83/32.png) [@khanfarabi1234](https://discuss.huggingface.co/u/khanfarabi1234)\
**Post date:** [May 24, 2022, 8:24pm UTC](https://discuss.huggingface.co/t/zero-shot-classification/18328/1 "2022-05-24T20:24:45Z")

</div>

According to my understanding the limitation of the zero-shot classifier is, zero-shot depends on the prior knowledge of the large data. Never-the-less, zero-shot performs poorly in case of dialog or conversation data ([yulongchen/DialogSum · Datasets at Hugging Face](https://huggingface.co/datasets/yulongchen/DialogSum/viewer/yulongchen--DialogSum/train)) where the topic inference accuracy of the zero-shot is around 50%. What I have understood is that, if any word or its synonym word list is not in the prior knowledge of the zero-shot, zero-shot makes wrong prediction. Thanks for your time.

Is it possible modify the zero-shot classifier?