README.md

---
language:
- nl
license: cc-by-nc-sa-4.0
tags:
- generated_from_trainer
- simplification
datasets:
- BramVanroy/chatgpt-dutch-simplification
metrics:
- rouge
- sari
task_categories:
- text2text-generation
task_ids:
- text-simplification
widget:
- example_title: Cooking
  text: Op bepaalde tijdstippen verlang ik naar de smaakvolle culinaire creaties welke
    door de ambachtelijke expertise van mijn grootmoeder zijn vervaardigd.
base_model: yhavinga/ul2-base-dutch
model-index:
- name: BramVanroy/ul2-base-dutch-simplification-mai-2023
  results:
  - task:
      type: text-simplification
      name: Text Simplification
    dataset:
      name: ChatGPT Dutch Simplification
      type: BramVanroy/chatgpt-dutch-simplification
    metrics:
    - type: rouge
      value: 41.5749
      name: Eval Rouge-1
    - type: rouge
      value: 19.9
      name: Eval Rouge-2
    - type: rouge
      value: 36.3204
      name: Eval RougeL
    - type: rouge
      value: 36.2596
      name: Eval RougeLsum
    - type: sari
      value: 53.0091
      name: Eval SARI
    - type: rouge
      value: 44.2877
      name: Test Rouge-1
    - type: rouge
      value: 20.8132
      name: Test Rouge-2
    - type: rouge
      value: 39.0951
      name: Test RougeL
    - type: rouge
      value: 39.2709
      name: Test RougeLsum
    - type: sari
      value: 52.9621
      name: Test SARI
---


# ul2-base-dutch-simplification-mai-2023

This model is intended to simplify Dutch sentences.

This model is a fine-tuned version of [yhavinga/ul2-base-dutch](https://huggingface.co/yhavinga/ul2-base-dutch) on
the [BramVanroy/chatgpt-dutch-simplification](https://huggingface.co/datasets/BramVanroy/chatgpt-dutch-simplification)
dataset. 

The model was created in light of the master thesis of Charlotte Van de Velde in the Master of Science in Artificial
Intelligence (MAI) at KU Leuven in 2023. Charlotte is supervised by Vincent Vandeghinste and Bram Vanroy. 
Dataset creation by Charlotte, model training by Bram.

## Quick links

- [Repository](https://github.com/BramVanroy/mai-simplification-nl-2023#22-hyperparameter-sweep): includes training code and model creation log
- [Dataset](https://huggingface.co/datasets/BramVanroy/chatgpt-dutch-simplification): `BramVanroy/chatgpt-dutch-simplification`
- [Parent model](https://huggingface.co/yhavinga/ul2-base-dutch): this model was finetuned on `yhavinga/ul2-base-dutch`
- [Demo](https://huggingface.co/spaces/BramVanroy/mai-simplification-nl-2023-demo): shows the this model in action (don't rely on the "Hosted inference API" widget on this page, it does not work very well)

## Intended uses & limitations, and dataset

The model is intended for sentence-level simplification of Dutch. It might extend to document-level simplification
but most of the dataset is limited to sentences so document-level performance is not guaranteed.

The dataset has been generated automatically (cf.
[dataset description](https://huggingface.co/datasets/BramVanroy/chatgpt-dutch-simplification)) and has not been
manually verified. On top of that, this model has been fine-tuned and we did not scrutinize the parent model or its
training data. Output of the current model is therefore subject to unexpected results (as most if not all neural
networks).

Because the dataset was generated with ChatGPT, this model cannot be used for commercial purposes.

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 0.00026885245616406115
- train_batch_size: 12
- optimizer: Adafactor
- num_epochs: 26

These hyperarameters were found through Bayesian hyperparameter search with `wandb`. This is described in the
[repository](https://github.com/BramVanroy/mai-simplification-nl-2023#22-hyperparameter-sweep).

### Training results

`eval` results are on the evaluation set, `predict` results are on the test set. These were achieved with
beam search (num_beams=3).

```json
{
    "eval_gen_len": 21.206349206349206,
    "eval_loss": 2.598172903060913,
    "eval_rouge1": 41.5749,
    "eval_rouge2": 19.9,
    "eval_rougeL": 36.3204,
    "eval_rougeLsum": 36.2596,
    "eval_sari": 53.0091,
  
    "predict_gen_len": 22.40625,
    "predict_loss": 2.517918586730957,
    "predict_rouge1": 44.2877,
    "predict_rouge2": 20.8132,
    "predict_rougeL": 39.0951,
    "predict_rougeLsum": 39.2709,
    "predict_sari": 52.9621
}
```


### Framework versions

- Transformers 4.29.2
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3