language: Deustch Italian
tags:
- translation Deustch Italian model
datasets:
- dcep europarl jrc-acquis
widget:
- text: >-
Die Mitgliedstaaten müssen bei Verstößen gegen die Pflicht, beim
Überschreiten der Außengrenzen der Europäischen Union Bewegungen von
Barmitteln anzumelden, wirksame, angemessene und abschreckende Strafen
verhängen.
legal_t5_small_trans_de_it model
Model on translating legal text from Deustch to Italian. It was first released in this repository. This model is trained on three parallel corpus from jrc-acquis, europarl and dcep.
Model description
legal_t5_small_trans_de_it is based on the t5-small
model and was trained on a large corpus of parallel text. This is a smaller model, which scales the baseline model of t5 down by using dmodel = 512
, dff = 2,048
, 8-headed attention, and only 6 layers each in the encoder and decoder. This variant has about 60 million parameters.
Intended uses & limitations
The model could be used for translation of legal texts from Deustch to Italian.
How to use
Here is how to use this model to translate legal text from Deustch to Italian in PyTorch:
from transformers import AutoTokenizer, AutoModelWithLMHead, TranslationPipeline
pipeline = TranslationPipeline(
model=AutoModelWithLMHead.from_pretrained("SEBIS/legal_t5_small_trans_de_it"),
tokenizer=AutoTokenizer.from_pretrained(pretrained_model_name_or_path = "SEBIS/legal_t5_small_trans_de_it", do_lower_case=False,
skip_special_tokens=True),
device=0
)
de_text = "Die Mitgliedstaaten müssen bei Verstößen gegen die Pflicht, beim Überschreiten der Außengrenzen der Europäischen Union Bewegungen von Barmitteln anzumelden, wirksame, angemessene und abschreckende Strafen verhängen."
pipeline([de_text], max_length=512)
Training data
The legal_t5_small_trans_de_it model was trained on JRC-ACQUIS, EUROPARL, and DCEP dataset consisting of 5 Million parallel texts.
Training procedure
Preprocessing
Pretraining
An unigram model with 88M parameters is trained over the complete parallel corpus to get the vocabulary (with byte pair encoding), which is used with this model.
Evaluation results
When the model is used for translation test dataset, achieves the following results:
Test results :
Model | BLEU score |
---|---|
legal_t5_small_trans_de_it | 43.3 |