# Fintuning Transformer on CLEF dataset

**URL:** <https://discuss.huggingface.co/t/fintuning-transformer-on-clef-dataset/9584>\
**Category:** 🤗Transformers\
**Created:** [August 30, 2021, 8:13am UTC](https://discuss.huggingface.co/t/fintuning-transformer-on-clef-dataset/9584 "2021-08-30T08:13:39Z")\
**Posts on this page:** 1\
**Showing post:** 7

<div class="post-metadata">

**Author:** ![lewtun](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/lewtun/32/30995_2.png) [@lewtun](https://discuss.huggingface.co/u/lewtun)\
**Post date:** [September 2, 2021, 11:46am UTC](https://discuss.huggingface.co/t/fintuning-transformer-on-clef-dataset/9584/7 "2021-09-02T11:46:44Z")

</div>

One other thing regarding long-contexts: you can also try using a sliding window approach as suggested in [this thread](https://discuss.huggingface.co/t/longformer-and-sentiment-analysis/9416/6).

This is actually how the question-answering pipelines are able to handle long contexts and I think the above suggestion could also work nicely in your case 🙂

---

_[View the full topic](https://discuss.huggingface.co/t/fintuning-transformer-on-clef-dataset/9584)._
