# Summarization for survey open end questions

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fsummarization-for-survey-open-end-questions%2F70965%3E%5C
**Category:** 🤗Transformers\
**Created:** [January 29, 2024, 1:29am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fsummarization-for-survey-open-end-questions%2F70965 "2024-01-29T01:29:28Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![neoiris](https://avatars.discourse-cdn.com/v4/letter/n/cab0a1/32.png) [@neoiris](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fneoiris)%5C
**Post date:** [January 29, 2024, 1:29am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fsummarization-for-survey-open-end-questions%2F70965%2F1 "2024-01-29T01:29:28Z")

</div>

Hi I’m working in HR and would like to summarize key topics in employee questionnaire.  
Let’s say there is a question " what effort is required to improve onboarding experience for new hire?" . There are 6000 replies and each answers ranges from 3 words to 200 words. Because this is not a single document but multiple documents, I consolidated all comments into single document and applied various summarization model(T5, Bart…). However, the summary result does not look correct. Can I ask if there is a model/method which reads multiple documents and provide a summary or topic?

Thanks