rufimelo's picture
Update README.md
21db10e
metadata
language:
  - pt
thumbnail: Portuguese BERT for the Legal Domain
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - transformers
datasets:
  - assin
  - assin2
  - stsb_multi_mt
  - rufimelo/PortugueseLegalSentences-v2
widget:
  - source_sentence: O advogado apresentou as provas ao juíz.
    sentences:
      - O juíz leu as provas.
      - O juíz leu o recurso.
      - O juíz atirou uma pedra.
    example_title: Example 1
model-index:
  - name: BERTimbau
    results:
      - task:
          name: STS
          type: STS
        metrics:
          - name: Pearson Correlation - assin Dataset
            type: Pearson Correlation
            value: xxxx
          - name: Pearson Correlation - assin2 Dataset
            type: Pearson Correlation
            value: xxxxx
          - name: Pearson Correlation - stsb_multi_mt pt Dataset
            type: pearsonr
            value: xxxxx

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

Model Assin Assin2 stsb_multi_mt pt avg
Legal-BERTimbau-sts-base 0.71457 0.73545 0.72383 0.72462
Legal-BERTimbau-sts-base-ma 0.74874 0.79532 0.82254 0.78886
Legal-BERTimbau-sts-base-ma-v2 0.75481 0.80262 0.82178 0.79307
Legal-BERTimbau-base-TSDAE-sts 0.78814 0.81380 0.75777 0.78657
Legal-BERTimbau-sts-large 0.76629 0.82357 0.79120 0.79369
Legal-BERTimbau-sts-large-v2 0.76299 0.81121 0.81726 0.79715
Legal-BERTimbau-sts-large-ma 0.76195 0.81622 0.82608 0.80142
Legal-BERTimbau-sts-large-ma-v2 0.7836 0.8462 0.8261 0.81863
Legal-BERTimbau-sts-large-ma-v3 0.7749 0.8470 0.8364 0.81943
Legal-BERTimbau-large-v2-sts 0.71665 0.80106 0.73724 0.75165
Legal-BERTimbau-large-TSDAE-sts 0.72376 0.79261 0.73635 0.75090
Legal-BERTimbau-large-TSDAE-sts-v2 0.81326 0.83130 0.786314 0.81029
Legal-BERTimbau-large-TSDAE-sts-v3 0.80703 0.82270 0.77638 0.80204
---------------------------------------- ---------- ---------- ---------- ----------
BERTimbau base Fine-tuned for STS 0.78455 0.80626 0.82841 0.80640
BERTimbau large Fine-tuned for STS 0.78193 0.81758 0.83784 0.81245
---------------------------------------- ---------- ---------- ---------- ----------
paraphrase-multilingual-mpnet-base-v2 0.71457 0.79831 0.83999 0.78429
paraphrase-multilingual-mpnet-base-v2 Fine-tuned with assin(s) 0.77641 0.79831 0.84575 0.80682

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}
}