# Using summarization models for paraphrasing

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fusing-summarization-models-for-paraphrasing%2F2513%3E%5C
**Category:** 🤗Transformers\
**Created:** [December 4, 2020, 6:08am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fusing-summarization-models-for-paraphrasing%2F2513 "2020-12-04T06:08:38Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![prajjwal1](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/prajjwal1/32/2246_2.png) [@prajjwal1](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fprajjwal1)%5C
**Post date:** [December 4, 2020, 6:08am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fusing-summarization-models-for-paraphrasing%2F2513%2F1 "2020-12-04T06:08:38Z")

</div>

I’m using summarization models for short sentences. I found that summarization models do not change the sentences much (many times, they are kept intact) for short sentences. I saw some models on model-hub which are finetuned for performing paraphrasing. I did not see any information on how it was done. Can you please share how to finetune summarization models for better paraphrasing of short sequences (\<128) ?