---
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-large-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: 41.3871
        name: Eval Rouge-1
      - type: rouge
        value: 19.6751
        name: Eval Rouge-2
      - type: rouge
        value: 36.0469
        name: Eval RougeL
      - type: rouge
        value: 36.1178
        name: Eval RougeLsum
      - type: sari
        value: 54.3588
        name: Eval SARI
      - type: rouge
        value: 43.8191
        name: Test Rouge-1
      - type: rouge
        value: 21.7783
        name: Test Rouge-2
      - type: rouge
        value: 39.3657
        name: Test RougeL
      - type: rouge
        value: 39.3751
        name: Test RougeLsum
      - type: sari
        value: 52.3752
        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-large-dutch-simplification-mai-2023

This model is intended to simplify Dutch sentences.

This model is a fine-tuned version of [yhavinga/ul2-large-dutch](https://huggingface.co/yhavinga/ul2-large-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-large-dutch): this model was finetuned on `yhavinga/ul2-large-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: 0.0002927210895006501
- train_batch_size: 32
- optimizer: Adafactor
- num_epochs: 27

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": 21.404761904761905,
    "eval_loss": 3.0882697105407715,
    "eval_rouge1": 41.3871,
    "eval_rouge2": 19.6751,
    "eval_rougeL": 36.0469,
    "eval_rougeLsum": 36.1178,
    "eval_sari": 54.3588,
  
    "predict_gen_len": 22.1484375,
    "predict_loss": 2.7822625637054443,
    "predict_rouge1": 43.8191,
    "predict_rouge2": 21.7783,
    "predict_rougeL": 39.3657,
    "predict_rougeLsum": 39.3751,
    "predict_sari": 52.3752
}
```

Note: the model seems to underperform compared to the
[base variant](https://huggingface.co/BramVanroy/ul2-small-dutch-simplification-mai-2023) of the model, achieving only
similar results with a much larger size. The reason for this may be found in the hyperparameters, where
this large model may have benefitted from a smaller learning rate in the optimisation space. In the hyperparameter 
search, the learning rate spectrum was set to 1e-03 to 1e-04 but this might be too large for this model and size. 

### Framework versions

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