---
license: cc-by-nc-sa-4.0
tags:
  - generated_from_trainer
  - simplification
task_categories:
  - text2text-generation
task_ids:
  - text-simplification
language:
  - nl
datasets:
  - BramVanroy/chatgpt-dutch-simplification
metrics:
  - rouge
  - sari
model-index:
- name: BramVanroy/ul2-small-dutch-simplification-mai-2023
  results:
  - task:
      type: text-simplification
      name: Text Simplification
    dataset:
      type: BramVanroy/chatgpt-dutch-simplification
      name: ChatGPT Dutch Simplification
    metrics:
      - type: rouge
        value: 40.9663
        name: Eval Rouge-1
      - type: rouge
        value: 18.499
        name: Eval Rouge-2
      - type: rouge
        value: 34.9342
        name: Eval RougeL
      - type: rouge
        value: 34.9752
        name: Eval RougeLsum
      - type: sari
        value: 52.4509
        name: Eval SARI
      - type: rouge
        value: 39.6138
        name: Test Rouge-1
      - type: rouge
        value: 17.1242
        name: Test Rouge-2
      - type: rouge
        value: 35.4629
        name: Test RougeL
      - type: rouge
        value: 35.3679
        name: Test RougeLsum
      - type: sari
        value: 51.7538
        name: Test SARI
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."

---


# ul2-small-dutch-simplification-mai-2023

This model is intended to simplify Dutch sentences.

This model is a fine-tuned version of [yhavinga/ul2-small-dutch](https://huggingface.co/yhavinga/ul2-small-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-small-dutch): this model was finetuned on `yhavinga/ul2-small-dutch`
- [Demo](https://huggingface.co/spaces/BramVanroy/mai-simplification-nl-2023-demo): shows the "base" 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: 0.0006370158604635734
- train_batch_size: 20
- optimizer: Adafactor
- num_epochs: 37

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": 21.555555555555557,
    "eval_loss": 3.2290523052215576,
    "eval_rouge1": 40.9663,
    "eval_rouge2": 18.499,
    "eval_rougeL": 34.9342,
    "eval_rougeLsum": 34.9752,
    "eval_sari": 52.4509,
  
    "predict_gen_len": 21.796875,
    "predict_loss": 3.063812494277954,
    "predict_rouge1": 39.6138,
    "predict_rouge2": 17.1242,
    "predict_rougeL": 35.4629,
    "predict_rougeLsum": 35.3679,
    "predict_sari": 51.7538
}
```


### Framework versions

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