Work developed as part of Project IRIS.

Thesis: A Semantic Search System for Supremo Tribunal de Justiça

stjiris/bert-large-portuguese-cased-legal-mlm-mkd-nli-sts-v0 (Legal BERTimbau)

This is a sentence-transformers model: It maps sentences & paragraphs to a 1024 dimensional dense vector space and can be used for tasks like clustering or semantic search. stjiris/bert-large-portuguese-cased-legal-mlm-mkd-nli-sts-v0 derives from stjiris/bert-large-portuguese-cased-legal-mlm (legal variant of BERTimbau large).

It was trained using the MLM technique with a learning rate 1e-5 Legal Sentences from +-30000 documents 15000 training steps (best performance for our semantic search system implementation)

This model was subjected to Multilingual Knowledge Distillation technique (mkd). For the Multilingual Knowledge Distillation process, the teacher model was 'sentence-transformers/stsb-roberta-large', the supposed supported language as English and the language to learn was portuguese The dataset used was: TED 2020 – Parallel Sentences Corpus. TED 2020 contains around 4000 TED and TED-X transcripts from July 2020. These transcripts were translated by volunteers into more than 100 languages, adding up to a total of 10 544 174 sentences.

The model was presented to NLI data. 16 batch size, 2e-5 lr

It was trained for Semantic Textual Similarity, being submitted to a fine tuning stage with the assin, assin2, stsb_multi_mt pt datasets. 'lr': 1e-5

Usage (Sentence-Transformers)

Using this model becomes easy when you have sentence-transformers installed:

pip install -U sentence-transformers

Then you can use the model like this:

from sentence_transformers import SentenceTransformer
sentences = ["Isto é um exemplo", "Isto é um outro exemplo"]

model = SentenceTransformer('stjiris/bert-large-portuguese-cased-legal-mlm-mkd-nli-sts-v0')
embeddings = model.encode(sentences)
print(embeddings)

Usage (HuggingFace Transformers)

from transformers import AutoTokenizer, AutoModel
import torch


#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)

# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']

# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('stjiris/bert-large-portuguese-cased-legal-mlm-mkd-nli-sts-v0')
model = AutoModel.from_pretrained('stjiris/bert-large-portuguese-cased-legal-mlm-mkd-nli-sts-v0')

# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')

# Compute token embeddings
with torch.no_grad():
    model_output = model(**encoded_input)
# Perform pooling. In this case, mean pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 514, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 1028, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False})
)

Citing & Authors

Contributions

@rufimelo99

If you use this work, please cite:

@inproceedings{MeloSemantic,
    author = {Melo, Rui and Santos, Professor Pedro Alexandre and Dias, Professor Jo{\~ a}o},
    title = {A {Semantic} {Search} {System} for {Supremo} {Tribunal} de {Justi}{\c c}a},
}

@inproceedings{souza2020bertimbau,
  author    = {F{\'a}bio Souza and
               Rodrigo Nogueira and
               Roberto Lotufo},
  title     = {{BERT}imbau: pretrained {BERT} models for {B}razilian {P}ortuguese},
  booktitle = {9th Brazilian Conference on Intelligent Systems, {BRACIS}, Rio Grande do Sul, Brazil, October 20-23 (to appear)},
  year      = {2020}
}

@inproceedings{fonseca2016assin,
  title={ASSIN: Avaliacao de similaridade semantica e inferencia textual},
  author={Fonseca, E and Santos, L and Criscuolo, Marcelo and Aluisio, S},
  booktitle={Computational Processing of the Portuguese Language-12th International Conference, Tomar, Portugal},
  pages={13--15},
  year={2016}
}

@inproceedings{real2020assin,
  title={The assin 2 shared task: a quick overview},
  author={Real, Livy and Fonseca, Erick and Oliveira, Hugo Goncalo},
  booktitle={International Conference on Computational Processing of the Portuguese Language},
  pages={406--412},
  year={2020},
  organization={Springer}
}
@InProceedings{huggingface:dataset:stsb_multi_mt,
title = {Machine translated multilingual STS benchmark dataset.},
author={Philip May},
year={2021},
url={https://github.com/PhilipMay/stsb-multi-mt}
}