gsarti's picture
Update README.md
32f9b4a
|
raw
history blame
4.08 kB
metadata
language:
  - it
license: apache-2.0
tags:
  - italian
  - sequence-to-sequence
  - style-transfer
  - efficient
  - formality-style-transfer
datasets:
  - yahoo/xformal_it
widget:
  - text: Questa performance è a dir poco spiacevole.
  - text: >-
      In attesa di un Suo cortese riscontro, Le auguriamo un piacevole
      proseguimento di giornata.
  - text: Questa visione mi procura una goduria indescrivibile.
  - text: qualora ciò possa interessarti, ti pregherei di contattarmi.
metrics:
  - rouge
  - bertscore
model-index:
  - name: it5-efficient-small-el32-formal-to-informal
    results:
      - task:
          type: formality-style-transfer
          name: Formal-to-informal Style Transfer
        dataset:
          type: xformal_it
          name: XFORMAL (Italian Subset)
        metrics:
          - type: rouge1
            value: 0.459
            name: Avg. Test Rouge1
          - type: rouge2
            value: 0.244
            name: Avg. Test Rouge2
          - type: rougeL
            value: 0.435
            name: Avg. Test RougeL
          - type: bertscore
            value: 0.739
            name: Avg. Test BERTScore
            args:
              - model_type: dbmdz/bert-base-italian-xxl-uncased
              - lang: it
              - num_layers: 10
              - rescale_with_baseline: true
              - baseline_path: bertscore_baseline_ita.tsv

IT5 Cased Small Efficient EL32 for Formal-to-informal Style Transfer 🤗

Shout-out to Stefan Schweter for contributing the pre-trained efficient model!

This repository contains the checkpoint for the IT5 Cased Small Efficient EL32 model fine-tuned on Formal-to-informal style transfer on the Italian subset of the XFORMAL dataset as part of the experiments of the paper IT5: Large-scale Text-to-text Pretraining for Italian Language Understanding and Generation by Gabriele Sarti and Malvina Nissim.

Efficient IT5 models differ from the standard ones by adopting a different vocabulary that enables cased text generation and an optimized model architecture to improve performances while reducing parameter count. The Small-EL32 replaces the original encoder from the T5 Small architecture with a 32-layer deep encoder, showing improved performances over the base model.

A comprehensive overview of other released materials is provided in the gsarti/it5 repository. Refer to the paper for additional details concerning the reported scores and the evaluation approach.

Using the model

Model checkpoints are available for usage in Tensorflow, Pytorch and JAX. They can be used directly with pipelines as:

from transformers import pipelines

f2i = pipeline("text2text-generation", model='it5/it5-efficient-small-el32-formal-to-informal')
f2i("Vi ringrazio infinitamente per vostra disponibilità")
>>> [{"generated_text": "e grazie per la vostra disponibilità!"}]

or loaded using autoclasses:

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("it5-efficient-small-el32-formal-to-informal")
model = AutoModelForSeq2SeqLM.from_pretrained("it5-efficient-small-el32-formal-to-informal")

If you use this model in your research, please cite our work as:

@article{sarti-nissim-2022-it5,
    title={{IT5}: Large-scale Text-to-text Pretraining for Italian Language Understanding and Generation},
    author={Sarti, Gabriele and Nissim, Malvina},
    journal={ArXiv preprint 2203.03759},
    url={https://arxiv.org/abs/2203.03759},
    year={2022},
    month={mar}
}

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 0.0003
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 10.0

Framework versions

  • Transformers 4.15.0
  • Pytorch 1.10.0+cu102
  • Datasets 1.17.0
  • Tokenizers 0.10.3