自然语言推理的交叉编码器

此模型使用 SentenceTransformers Cross-Encoder 类进行训练。该模型基于 microsoft/deberta-v3-base 。

训练数据

模型在 SNLI 和 MultiNLI 数据集上进行了训练。对于给定的句子对，它会输出三个与标签（矛盾、蕴含、中性）对应的分数。

性能

• SNLI 测试数据集准确率：92.38
• MNLI 不匹配集准确率：90.04

更多评估结果，请参见 SBERT.net - Pretrained Cross-Encoder 。

用法

可以像这样使用预训练模型：

from sentence_transformers import CrossEncoder
model = CrossEncoder('cross-encoder/nli-deberta-v3-base')
scores = model.predict([('A man is eating pizza', 'A man eats something'), ('A black race car starts up in front of a crowd of people.', 'A man is driving down a lonely road.')])

#Convert scores to labels
label_mapping = ['contradiction', 'entailment', 'neutral']
labels = [label_mapping[score_max] for score_max in scores.argmax(axis=1)]

与 Transformers AutoModel 的使用

您还可以直接使用 Transformers 库中的模型（而无需使用 SentenceTransformers 库）：

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

model = AutoModelForSequenceClassification.from_pretrained('cross-encoder/nli-deberta-v3-base')
tokenizer = AutoTokenizer.from_pretrained('cross-encoder/nli-deberta-v3-base')

features = tokenizer(['A man is eating pizza', 'A black race car starts up in front of a crowd of people.'], ['A man eats something', 'A man is driving down a lonely road.'],  padding=True, truncation=True, return_tensors="pt")

model.eval()
with torch.no_grad():
    scores = model(**features).logits
    label_mapping = ['contradiction', 'entailment', 'neutral']
    labels = [label_mapping[score_max] for score_max in scores.argmax(dim=1)]
    print(labels)

零样本分类

该模型还可以用于零样本分类：

from transformers import pipeline

classifier = pipeline("zero-shot-classification", model='cross-encoder/nli-deberta-v3-base')

sent = "Apple just announced the newest iPhone X"
candidate_labels = ["technology", "sports", "politics"]
res = classifier(sent, candidate_labels)
print(res)