Skip to content

Latest commit

 

History

20 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Intent-classification-Polish-language

A deep learning solution for intent classification problem in the domain of Polish language.

Approach

Intent classification is done by using a HerBERT as a backbone language model to understand the utterances. On top of that, a custom intent classification head is used to output the utterance intent.

Dataset

MASSIVE: https://arxiv.org/pdf/2204.08582.pdf

Useful files

  • train.py - train code
  • test.py - test code with csv export for further usage in the analytics.py
  • analytics.py - code that extracts interesting information about the trained model, it uses the csv file exported using test.py code
  • models/best_model - this folder contains the config and model definition for a training setting, that achieved ~86% validation accuracy

About

Intent classification using HerBERT language model and a custom intent classification head.

Resources

Stars

0 stars

Watchers

1 watching

Forks

Releases

Packages

Contributors

Languages