Bert Large Portuguese Cased Legal Tsdae Gpl Nli Sts MetaKD V1

🚀 stjiris/bert-large-portuguese-cased-legal-tsdae-gpl-nli-sts-MetaKD-v1（法律領域的葡萄牙語BERT）

這是一個用於法律領域的葡萄牙語BERT模型，它能將句子和段落映射到一個1024維的密集向量空間，可用於聚類或語義搜索等任務。該模型基於特定技術和數據集進行訓練，在語義文本相似度任務上表現出色。

🚀 快速開始

使用此模型，你需要先安裝 sentence-transformers：

pip install -U sentence-transformers

然後可以按如下方式使用模型：

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

model = SentenceTransformer('stjiris/bert-large-portuguese-cased-legal-tsdae-gpl-nli-sts-MetaKD-v1')
embeddings = model.encode(sentences)
print(embeddings)

✨ 主要特性

• 向量映射：將句子和段落映射到1024維的密集向量空間。
• 多任務適用：可用於聚類、語義搜索等任務。
• 多階段訓練：採用TSDAE技術、Generative Pseudo Labeling訓練、NLI數據訓練以及語義文本相似度微調等多階段訓練方式。
• 知識蒸餾：經過Metadata Knowledge Distillation處理，提高信息檢索性能。

📦 安裝指南

使用此模型，你需要先安裝 sentence-transformers：

pip install -U sentence-transformers

💻 使用示例

基礎用法

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

model = SentenceTransformer('stjiris/bert-large-portuguese-cased-legal-tsdae-gpl-nli-sts-MetaKD-v1')
embeddings = model.encode(sentences)
print(embeddings)

高級用法

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-tsdae-gpl-nli-sts-MetaKD-v1')
model = AutoModel.from_pretrained('stjiris/bert-large-portuguese-cased-legal-tsdae-gpl-nli-sts-MetaKD-v1')

# 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)

🔧 技術細節

模型架構

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})
)

訓練過程

• TSDAE訓練：使用TSDAE技術，學習率為1e-5，使用約30000篇文檔中的法律句子，進行212k個訓練步驟。
• Generative Pseudo Labeling訓練：對模型進行Generative Pseudo Labeling訓練。
• NLI數據訓練：使用NLI數據進行訓練，批量大小為16，學習率為2e-5。
• 語義文本相似度微調：使用 assin、assin2、stsb_multi_mt pt 數據集進行語義文本相似度微調，學習率為1e-5。
• Metadata Knowledge Distillation：對模型進行Metadata Knowledge Distillation處理。

評估指標

📄 許可證

本項目採用MIT許可證。

📚 詳細文檔

引用與作者

貢獻者

@rufimelo99

引用信息

如果你使用了本項目，請引用以下文獻：

@InProceedings{MeloSemantic,
  author="Melo, Rui
  and Santos, Pedro A.
  and Dias, Jo{\~a}o",
  editor="Moniz, Nuno
  and Vale, Zita
  and Cascalho, Jos{\'e}
  and Silva, Catarina
  and Sebasti{\~a}o, Raquel",
  title="A Semantic Search System for the Supremo Tribunal de Justi{\c{c}}a",
  booktitle="Progress in Artificial Intelligence",
  year="2023",
  publisher="Springer Nature Switzerland",
  address="Cham",
  pages="142--154",
  abstract="Many information retrieval systems use lexical approaches to retrieve information. Such approaches have multiple limitations, and these constraints are exacerbated when tied to specific domains, such as the legal one. Large language models, such as BERT, deeply understand a language and may overcome the limitations of older methodologies, such as BM25. This work investigated and developed a prototype of a Semantic Search System to assist the Supremo Tribunal de Justi{\c{c}}a (Portuguese Supreme Court of Justice) in its decision-making process. We built a Semantic Search System that uses specially trained BERT models (Legal-BERTimbau variants) and a Hybrid Search System that incorporates both lexical and semantic techniques by combining the capabilities of BM25 and the potential of Legal-BERTimbau. In this context, we obtained a {\$}{\$}335{\backslash}{\%}{\$}{\$}335{\%}increase on the discovery metric when compared to BM25 for the first query result. This work also provides information on the most relevant techniques for training a Large Language Model adapted to Portuguese jurisprudence and introduces a new technique of Metadata Knowledge Distillation.",
  isbn="978-3-031-49011-8"
}


@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}
}