# How to use additional input features for Abstractive summarization? Seq2Seq

**URL:** <https://discuss.huggingface.co/t/how-to-use-additional-input-features-for-abstractive-summarization-seq2seq/39964>\
**Category:** 🤗Transformers\
**Created:** [May 15, 2023, 3:18pm UTC](https://discuss.huggingface.co/t/how-to-use-additional-input-features-for-abstractive-summarization-seq2seq/39964 "2023-05-15T15:18:02Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![StivenLancheros](https://avatars.discourse-cdn.com/v4/letter/s/9de053/32.png) [@StivenLancheros](https://discuss.huggingface.co/u/StivenLancheros)\
**Post date:** [May 15, 2023, 3:18pm UTC](https://discuss.huggingface.co/t/how-to-use-additional-input-features-for-abstractive-summarization-seq2seq/39964/1 "2023-05-15T15:18:02Z")

</div>

Hello All,

I am trainning a length controlled abstractive summarizer and I would like to add the length of the golden summary as an additional feature for the model to learn the desired length. I saw the answer [here](https://discuss.huggingface.co/t/combine-bertforsequenceclassificaion-with-additional-features/6523) for classification in which a numeric feature is added to the hidden state of the [CLS] token. Since my problem is Seq2Seq language generation, does anyone have an idea on how to add this extra feature?  
I understand it should be added to the decoder which is the one generating the output, but if you guys know a better way or if Im incorrect please let me know.

Best regards,