Legal T5 Small Trans En Cs

🚀 legal_t5_small_trans_en_cs model

This is a model for translating legal text from English to Czech. It can effectively address the need for legal text translation between these two languages, providing a reliable solution for legal document processing. The model was first released in this repository and is trained on three parallel corpora from JRC-ACQUIS, Europarl, and DCEP.

✨ Features

• Based on the t5-small model, it is trained on a large parallel text corpus.
• A smaller model with about 60 million parameters, which scales down the baseline t5 model.
• Can be used for translating legal texts from English to Czech.

📦 Installation

The README doesn't provide specific installation steps, so this section is skipped.

💻 Usage Examples

Basic Usage

Here is how to use this model to translate legal text from English to Czech in PyTorch:

from transformers import AutoTokenizer, AutoModelWithLMHead, TranslationPipeline

pipeline = TranslationPipeline(
model=AutoModelWithLMHead.from_pretrained("SEBIS/legal_t5_small_trans_en_cs"),
tokenizer=AutoTokenizer.from_pretrained(pretrained_model_name_or_path = "SEBIS/legal_t5_small_trans_en_cs", do_lower_case=False, 
                                            skip_special_tokens=True),
    device=0
)

en_text = "1 In the countries concerned, this certainly affects the priority assigned to making progress on the issue of final disposal, particularly of highly radioactive waste and irradiated fuel elements."

pipeline([en_text], max_length=512)

📚 Documentation

Model description

The legal_t5_small_trans_en_cs model is based on the t5-small model and trained on a large corpus of parallel text. It is a smaller model that scales the baseline t5 model 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 is designed for the translation of legal texts from English to Czech.

Training data

The legal_t5_small_trans_en_cs model was trained on [JRC - ACQUIS](https://wt - public.emm4u.eu/Acquis/index_2.2.html), EUROPARL, and [DCEP](https://ec.europa.eu/jrc/en/language - technologies/dcep) datasets, which consist of 5 million parallel texts.

Training procedure

• Overall training: 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 approximately 220M parameters and was trained using the encoder - decoder architecture.
• 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:

BibTeX entry and citation info

Created by Ahmed Elnaggar/@Elnaggar_AI | [LinkedIn](https://www.linkedin.com/in/prof - ahmed - elnaggar/)