Bert Large Portuguese Cased Legal Tsdae Gpl Nli Sts MetaKD V1

🚀 stjiris/bert-large-portuguese-cased-legal-tsdae-gpl-nli-sts-MetaKD-v1 (Legal BERTimbau)

このモデルは、文や段落を1024次元の密ベクトル空間にマッピングし、クラスタリングや意味検索などのタスクに使用できるsentence - transformersモデルです。stjiris/bert-large-portuguese-cased-legal-tsdae-gpl-nli-sts-v0は、stjiris/bert-large-portuguese-cased-legal-tsdae（BERTimbau largeの法務用バリアント）に由来しています。

🚀 クイックスタート

このモデルは、sentence-transformersがインストールされていると簡単に使用できます。

pip install -U sentence-transformers

その後、次のようにモデルを使用できます。

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)

✨ 主な機能

• 文や段落を1024次元の密ベクトル空間にマッピングし、クラスタリングや意味検索などのタスクに使用可能。
• TSDAE技術を用いて学習率1e - 5で、約30000の文書からの法務用文で212kの学習ステップで学習。
• Generative Pseudo Labeling学習に供された。
• NLIデータで学習され、バッチサイズ16、学習率2e - 5。
• assin、assin2、stsb_multi_mt ptデータセットでSemantic Textual Similarityの微調整を行った。
• メタデータ知識蒸留（Metadata Knowledge Distillation）に供された。

📦 インストール

pip install -U sentence-transformers

💻 使用例

基本的な使用法

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)

高度な使用法

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)

📚 ドキュメント

モデル構造

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})
)

引用と著者

貢献者

@rufimelo99

この成果物を使用する場合は、以下を引用してください。

@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}
}

📄 ライセンス

このモデルはMITライセンスの下で提供されています。

関連リンク

• INESC - ID
• A Semantic Search System for Supremo Tribunal de Justiça
• Project IRIS
• A Semantic Search System for Supremo Tribunal de Justiça
• Metadata Knowledge Distillation Repository