Paecter

🚀 PaECTER - 專利相似度模型

PaECTER（使用引用信息感知Transformer的專利嵌入）是一個專利相似度模型。它基於谷歌的專利BERT作為基礎模型，能夠從專利文本中生成1024維的密集向量嵌入。這些向量封裝了給定專利文本的語義本質，非常適合用於與專利分析相關的各種下游任務。

論文鏈接：https://arxiv.org/pdf/2402.19411

✨ 主要特性

• 語義搜索
• 現有技術搜索
• 聚類分析
• 專利格局分析

🚀 快速開始

📦 安裝指南

若要使用此模型，你需要安裝 sentence-transformers：

pip install -U sentence-transformers

💻 使用示例

基礎用法（使用Sentence-Transformers）

from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]

model = SentenceTransformer('mpi-inno-comp/paecter')
embeddings = model.encode(sentences)
print(embeddings)

高級用法（使用HuggingFace Transformers）

若未安裝 sentence-transformers，可以按以下方式使用該模型：首先，將輸入數據傳入Transformer模型，然後對上下文詞嵌入應用正確的池化操作。

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('mpi-inno-comp/paecter')
model = AutoModel.from_pretrained('mpi-inno-comp/paecter')

# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt', max_length=512)

# 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

評估結果

該模型的評估詳情可在我們的論文 PaECTER: Patent-level Representation Learning using Citation-informed Transformers 中查看。

訓練細節

該模型使用以下參數進行訓練： 數據加載器： torch.utils.data.dataloader.DataLoader，長度為318750，參數如下：

{'batch_size': 4, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}

損失函數： sentence_transformers.losses.CustomTripletLoss.CustomTripletLoss，參數如下：

{'distance_metric': 'TripletDistanceMetric.EUCLIDEAN', 'triplet_margin': 1}

fit() 方法的參數：

{
    "epochs": 1,
    "evaluation_steps": 4000,
    "evaluator": "sentence_transformers.evaluation.TripletEvaluator.TripletEvaluator",
    "max_grad_norm": 1,
    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
    "optimizer_params": {
        "lr": 1e-05
    },
    "scheduler": "WarmupLinear",
    "steps_per_epoch": null,
    "warmup_steps": 31875.0,
    "weight_decay": 0.01
}

完整模型架構

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 1024, '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})
)

引用與作者

@misc{ghosh2024paecter,
      title={PaECTER: Patent-level Representation Learning using Citation-informed Transformers}, 
      author={Mainak Ghosh and Sebastian Erhardt and Michael E. Rose and Erik Buunk and Dietmar Harhoff},
      year={2024},
      eprint={2402.19411},
      archivePrefix={arXiv},
      primaryClass={cs.IR}
}

📄 許可證

本項目採用Apache 2.0許可證。