Negmpnet

🚀 NegMPNet

NegMPNet 是 all-mpnet-base-v2 的一个具备否定感知能力的版本。它是一个 sentence-transformers 模型，能够将句子和段落映射到 768 维的密集向量空间，可用于聚类或语义搜索等任务。如需了解更多信息，请参阅我们的论文 This is not correct! Negation-aware Evaluation of Language Generation Systems。

🚀 快速开始

本部分将指导你如何快速使用 NegMPNet 模型。

✨ 主要特性

• 否定感知能力：相较于基础模型，该模型对否定词有更好的敏感度。
• 向量映射功能：可将句子和段落映射到 768 维的密集向量空间。
• 多用途：适用于聚类、语义搜索等任务。

📦 安装指南

若要使用此模型，你需要安装 sentence-transformers，可使用以下命令进行安装：

pip install -U sentence-transformers

💻 使用示例

基础用法

使用 sentence-transformers 库调用模型的基础示例：

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

model = SentenceTransformer("tum-nlp/NegMPNet")
embeddings = model.encode(sentences)
print(embeddings)

高级用法

否定感知能力验证

此示例展示了该模型相较于基础模型在否定感知方面的优势：

from sentence_transformers import SentenceTransformer, util
import torch

base_model = SentenceTransformer("sentence-transformers/all-mpnet-base-v2")
finetuned_model = SentenceTransformer("tum-nlp/NegMPNet")

def cos_similarities(references: list, candidates: list, model: SentenceTransformer, batch_size=8) -> torch.Tensor:
    assert len(references) == len(candidates), "Number of references and candidates must be equal"
    emb_ref = model.encode(references, batch_size=batch_size)
    emb_cand = model.encode(candidates, batch_size=batch_size)
    return torch.diag(util.cos_sim(emb_ref, emb_cand))

references = ["Ray charles is legendary.", "Ray charles is legendary"]
candidates = ["Ray charles is a legend.", "Ray charles isn't legendary."]
print(cos_similarities(references, candidates, base_model)) # prints tensor([0.9453, 0.8683]) -> no negation-awareness
print(cos_similarities(references, candidates, finetuned_model)) # prints tensor([0.9585, 0.4263]) -> sensitive to negation

不使用 sentence-transformers 库的用法

若未安装 sentence-transformers 库，可按以下方式使用模型：

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("tum-nlp/NegMPNet")
model = AutoModel.from_pretrained("tum-nlp/NegMPNet")

# 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)

📚 详细文档

评估结果

若要对该模型进行自动化评估，可参考 Sentence Embeddings Benchmark：https://seb.sbert.net

训练参数

该模型的训练参数如下：

数据加载器

sentence_transformers.datasets.NoDuplicatesDataLoader.NoDuplicatesDataLoader，长度为 358，参数如下：

{'batch_size': 64}

损失函数

__main__.MultipleNegativesRankingLoss，参数如下：

{'scale': 20.0, 'similarity_fct': 'cos_sim'}

fit() 方法的参数

{
    "epochs": 1,
    "evaluation_steps": 35,
    "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
    "max_grad_norm": 1,
    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
    "optimizer_params": {
        "lr": 2e-05
    },
    "scheduler": "WarmupLinear",
    "steps_per_epoch": null,
    "warmup_steps": 36,
    "weight_decay": 0.01
}

完整模型架构

SentenceTransformer(
  (0): Transformer({'max_seq_length': 75, 'do_lower_case': False}) with Transformer model: MPNetModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)

📄 许可证

本模型采用 CC BY-SA 4.0 许可证。

🔖 引用

如果你使用了我们的模型，请引用我们的 INLG 2023 论文，BibTeX 引用格式如下：

@misc{anschütz2023correct,
      title={This is not correct! Negation-aware Evaluation of Language Generation Systems}, 
      author={Miriam Anschütz and Diego Miguel Lozano and Georg Groh},
      year={2023},
      eprint={2307.13989},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}