Bert Large Portuguese Cased Legal Tsdae Gpl Nli Sts V1

🚀 stjiris/bert-large-portuguese-cased-legal-tsdae-gpl-nli-sts-v1 (法律领域葡萄牙语BERT模型)

这是一个用于法律领域的葡萄牙语BERT模型，可将句子和段落映射到1024维的密集向量空间，适用于聚类或语义搜索等任务。

🚀 快速开始

本模型是一个 sentence-transformers 模型，它能把句子和段落映射到一个1024维的密集向量空间，可用于聚类、语义搜索等任务。stjiris/bert-large-portuguese-cased-legal-tsdae 模型基于 BERTimbau 大型模型衍生而来。

✨ 主要特性

• 基于 BERTimbau 大型模型，适用于葡萄牙语法律领域。
• 使用TSDAE技术进行训练，学习率为1e - 5，在约30000份文档的法律句子上进行了212k步训练。
• 经过生成式伪标签（Generative Pseudo Labeling）训练。
• 引入NLI数据进行训练，批次大小为16，学习率为2e - 5。
• 针对语义文本相似度进行训练，在 assin、assin2、stsb_multi_mt pt 和 IRIS STS 数据集上进行了微调。

📦 安装指南

若要使用该模型，需先安装 sentence-transformers：

pip install -U sentence-transformers

💻 使用示例

基础用法（Sentence - Transformers）

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-v1')
embeddings = model.encode(sentences)
print(embeddings)

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

🔧 技术细节

完整模型架构

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})
)

📚 详细文档

数据集

• stjiris/portuguese-legal-sentences-v0
• assin
• assin2
• stsb_multi_mt
• stjiris/IRIS_sts

模型评估结果

📄 许可证

本项目采用MIT许可证。

📝 引用与作者

贡献者

@rufimelo99

引用信息

如果您使用了本项目的成果，请引用以下文献：

@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}
}

项目相关链接

• INESC - ID
• A Semantic Search System for Supremo Tribunal de Justiça
• Project IRIS
• 论文：A Semantic Search System for Supremo Tribunal de Justiça