🚀 legal_t5_small_multitask_sv_en Model
A model for translating legal text from Swedish to English, offering efficient and accurate language conversion.
🚀 Quick Start
The legal_t5_small_multitask_sv_en
model is designed for translating legal text from Swedish to English. It was first released in this repository. The model is trained in parallel on three parallel corpora with 42 language pairs from JRC-ACQUIS, Europarl, and DCEP, along with an unsupervised task where the model follows the prediction task in a masked language model.
✨ Features
- Multitask Learning: No pretraining is involved. Instead, an unsupervised task is added to all translation tasks to achieve a multitask learning scenario.
- Intended Use: Ideal for translating legal texts from Swedish to English.
📦 Installation
No specific installation steps are provided in the original README. If you want to use this model in a Python environment, you need to install the transformers
library. You can install it using the following command:
pip install transformers
💻 Usage Examples
Basic Usage
Here is how to use this model to translate legal text from Swedish to English in PyTorch:
from transformers import AutoTokenizer, AutoModelWithLMHead, TranslationPipeline
pipeline = TranslationPipeline(
model=AutoModelWithLMHead.from_pretrained("SEBIS/legal_t5_small_multitask_sv_en"),
tokenizer=AutoTokenizer.from_pretrained(pretrained_model_name_or_path = "SEBIS/legal_t5_small_multitask_sv_en", do_lower_case=False,
skip_special_tokens=True),
device=0
)
sv_text = "inlämnat av följande ledamöter:"
pipeline([sv_text], max_length=512)
📚 Documentation
Model description
No pretraining is involved in case of legal_t5_small_multitask_sv_en
model. Instead, the unsupervised task is added with all the translation tasks to realize the multitask learning scenario.
Intended uses & limitations
The model could be used for translation of legal texts from Swedish to English.
🔧 Technical Details
Training data
The legal_t5_small_multitask_sv_en
model (the supervised task which involved only the corresponding language pair and as well as the unsupervised task where all of the data of all language pairs were available) was trained on JRC-ACQUIS, EUROPARL, and DCEP datasets consisting of 9 million parallel texts.
Training procedure
The model was trained on a single TPU Pod V3 - 8 for 250K steps in total, using a sequence length of 512 (batch size 4096). It has a total of approximately 220M parameters and was trained using the encoder - decoder architecture. The optimizer used is AdaFactor with an inverse square root learning rate schedule.
Preprocessing
An unigram model was trained with 88M lines of text from the parallel corpus (of all possible language pairs) to get the vocabulary (with byte pair encoding), which is used with this model.
📄 Evaluation results
When the model is used for the translation test dataset, it achieves the following results:
Model |
BLEU score |
legal_t5_small_multitask_sv_en |
36.195 |
BibTeX entry and citation info
Created by Ahmed Elnaggar/@Elnaggar_AI | LinkedIn