# Relation Extraction project: request for benchmarking suggestions

**URL:** <https://discourse.julialang.org/t/relation-extraction-project-request-for-benchmarking-suggestions/52705>\
**Category:** Offtopic\
**Created:** [January 1, 2021, 6:48pm UTC](https://discourse.julialang.org/t/relation-extraction-project-request-for-benchmarking-suggestions/52705 "2021-01-01T18:48:36Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![erratic](https://avatars.discourse-cdn.com/v4/letter/e/a9adbd/32.png) [@erratic](https://discourse.julialang.org/u/erratic)\
**Post date:** [January 1, 2021, 6:48pm UTC](https://discourse.julialang.org/t/relation-extraction-project-request-for-benchmarking-suggestions/52705/1 "2021-01-01T18:48:37Z")

</div>

Hello everyone,

I’m working on a project about relation extraction (RE).  
More specifically my project focus on a new method to improove training data to use with any (supervised) model for RE and I would like to benchmark my method testing it in pair with some state-of-the-art models for RE to check if I have a significant enhancement.

How can I benchmark my model properly (i.e. as a computer science paper would require)?  
Do I need the RE models working implementations? And If yes, where can I find it?  
Any help in how to proceed with benchmarking will be very apreciated 🙂