Bert Large Portuguese Cased Legal Mlm Nli Sts V1

🚀 stjiris/bert-large-portuguese-cased-legal-mlm-nli-sts-v1 (法律領域葡萄牙語BERT模型)

這是一個用於法律領域的葡萄牙語BERT模型，它可以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Sentence-Transformers框架，在多個葡萄牙語法律相關數據集上進行了訓練和微調，具有良好的語義文本相似度計算能力。

🚀 快速開始

本模型基於 sentence-transformers 框架，使用前請確保已安裝該庫：

pip install -U sentence-transformers

然後可以按照以下方式使用模型：

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

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

✨ 主要特性

• 多數據集訓練：模型在多個葡萄牙語法律相關數據集上進行了訓練，包括 assin、assin2、stsb_multi_mt pt 和 IRIS STS 等，能夠更好地處理法律領域的語義文本相似度任務。
• 語義向量映射：可以將句子和段落映射到一個1024維的密集向量空間，方便進行聚類、語義搜索等任務。
• 多種使用方式：支持使用 sentence-transformers 庫和 HuggingFace Transformers 庫進行調用。

📦 安裝指南

使用本模型需要安裝 sentence-transformers 庫，可通過以下命令進行安裝：

pip install -U sentence-transformers

💻 使用示例

基礎用法

使用 sentence-transformers 庫調用模型：

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

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

高級用法

使用 HuggingFace Transformers 庫調用模型：

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

📚 詳細文檔

模型信息

模型評估結果

🔧 技術細節

本模型基於 BERTimbau 大型模型的法律變體 stjiris/bert-large-portuguese-cased-legal-mlm 進行開發。訓練過程分為多個階段：

1. MLM訓練：使用MLM技術，學習率為1e-5，在約30000篇文檔的法律句子上進行了15000步訓練。
2. NLI數據處理：將模型應用於NLI數據，批量大小為16，學習率為2e-5。
3. 語義文本相似度微調：在 assin、assin2、stsb_multi_mt pt 和 IRIS STS 數據集上進行微調，學習率為1e-5。

完整模型架構

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})
)

📄 許可證

本模型使用MIT許可證。

📖 引用信息

貢獻者

@rufimelo99

引用格式

@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}
}

相關項目鏈接

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