英文

XLM-RoBERTa-large-XNLI-ANLI

XLM-RoBERTa-large模型在多个NLI数据集上进行微调,可用于零-shot分类。

下面是几个测试数据集的准确率:

XNLI-es XNLI-fr ANLI-R1 ANLI-R2 ANLI-R3
xlm-roberta-large-xnli-anli 93.7% 93.2% 68.5% 53.6% 49.0%

可以使用零-shot-classification管道加载模型,如下所示:

from transformers import pipeline
classifier = pipeline("zero-shot-classification", 
                       model="vicgalle/xlm-roberta-large-xnli-anli")

然后,您可以使用该管道将序列分类为您指定的任何类名:

sequence_to_classify = "Algún día iré a ver el mundo"
candidate_labels = ['viaje', 'cocina', 'danza']
classifier(sequence_to_classify, candidate_labels)
#{'sequence': 'Algún día iré a ver el mundo',
#'labels': ['viaje', 'danza', 'cocina'],
#'scores': [0.9991760849952698, 0.0004178212257102132, 0.0004059972707182169]}