GNER T5 Xl

🚀 重新思考生成式命名實體識別中的負樣本

本項目提出了生成式命名實體識別（GNER）框架，該框架在未見實體領域展現出強大的零樣本能力。在LLaMA和Flan - T5這兩個代表性生成模型上的實驗表明，在訓練過程中引入負樣本可顯著提升性能。由此得到的GNER - LLaMA和GNER - T5模型大幅超越了當前的最優方法，$F_1$分數分別提高了8分和11分。代碼和模型均已公開。

• 💻 代碼：https://github.com/yyDing1/GNER/
• 📖 論文：重新思考生成式命名實體識別中的負樣本
• 💾 HuggingFace Hub上的模型：GNER模型
• 🧪 復現材料：復現材料
• 🎨 Jupyter Notebook示例：GNER Notebook

✨ 主要特性

• 提出了GNER框架，具備增強的零樣本能力。
• 在訓練中引入負樣本，顯著提升模型性能。
• 基於LLaMA和Flan - T5的模型大幅超越當前最優方法。

📦 安裝指南

你需要安裝以下依賴：

pip install torch datasets deepspeed accelerate transformers protobuf

💻 使用示例

基礎用法

請參考Jupyter Notebook示例來使用GNER模型。

以下是一個使用GNER - T5的簡單推理示例：

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
>>> tokenizer = AutoTokenizer.from_pretrained("dyyyyyyyy/GNER-T5-xxl")
>>> model = AutoModelForSeq2SeqLM.from_pretrained("dyyyyyyyy/GNER-T5-xxl", torch_dtype=torch.bfloat16).cuda()
>>> model = model.eval()
>>> instruction_template = "Please analyze the sentence provided, identifying the type of entity for each word on a token-by-token basis.\nOutput format is: word_1(label_1), word_2(label_2), ...\nWe'll use the BIO-format to label the entities, where:\n1. B- (Begin) indicates the start of a named entity.\n2. I- (Inside) is used for words within a named entity but are not the first word.\n3. O (Outside) denotes words that are not part of a named entity.\n"
>>> sentence = "did george clooney make a musical in the 1980s"
>>> entity_labels = ["genre", "rating", "review", "plot", "song", "average ratings", "director", "character", "trailer", "year", "actor", "title"]
>>> instruction = f"{instruction_template}\nUse the specific entity tags: {', '.join(entity_labels)} and O.\nSentence: {sentence}"
>>> inputs = tokenizer(instruction, return_tensors="pt").to("cuda")
>>> outputs = model.generate(**inputs, max_new_tokens=640)
>>> response = tokenizer.decode(outputs[0], skip_special_tokens=True)
>>> print(response)
"did(O) george(B-actor) clooney(I-actor) make(O) a(O) musical(B-genre) in(O) the(O) 1980s(B-year)"

📚 詳細文檔

預訓練模型

我們發佈了基於LLaMA（7B）和Flan - T5（base、large、xl和xxl）的五個GNER模型。

📄 許可證

本項目採用Apache - 2.0許可證。

🔗 引用

@misc{ding2024rethinking,
      title={Rethinking Negative Instances for Generative Named Entity Recognition}, 
      author={Yuyang Ding and Juntao Li and Pinzheng Wang and Zecheng Tang and Bowen Yan and Min Zhang},
      year={2024},
      eprint={2402.16602},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}