rufimelo/Legal-BERTimbau-large-TSDAE-v4-GPL-sts

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. rufimelo/Legal-BERTimbau-large-TSDAE-v4-GPL-sts is based on Legal-BERTimbau-large which derives from BERTimbau large. It is adapted to the Portuguese legal domain and trained for STS on portuguese datasets.

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('rufimelo/Legal-BERTimbau-large-TSDAE-v4-GPL-sts')
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('rufimelo/Legal-BERTimbau-large-TSDAE-v4-GPL-sts')
model = AutoModel.from_pretrained('rufimelo/Legal-BERTimbau-large-TSDAE-v4-GPL-sts')

# 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)

Evaluation Results STS

Training

rufimelo/Legal-BERTimbau-large-TSDAE-sts-v3 is based on rufimelo/Legal-BERTimbau-large-TSDAE-sts-v3 which derives from BERTimbau large.

rufimelo/Legal-BERTimbau-large-TSDAE-v4-GPL-sts was trained with TSDAE: 200000 cleaned documents (https://huggingface.co/datasets/rufimelo/PortugueseLegalSentences-v1) 'lr': 1e-5

It was used GPL technique where batch = 4, epoch = 1, lr = 2e-5 and as to simulate the Cross-Encoder: rufimelo/Legal-BERTimbau-sts-large-v2 with dot product

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

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 768, '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

If you use this work, please cite BERTimbau's work:

@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}
}