BERT 使用拥抱面部模型的分数将“SpanAnnotation”转换为答案

Question

我正在关注从 huggingface 导入预训练的 model 问题和答案 model 的文档

from transformers import BertTokenizer, BertForQuestionAnswering
import torch
tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
model = BertForQuestionAnswering.from_pretrained('bert-base-uncased')
question, text = "Who was Jim Henson?", "Jim Henson was a nice puppet"
inputs = tokenizer(question, text, return_tensors='pt')
start_positions = torch.tensor([1])
end_positions = torch.tensor([3])
outputs = model(**inputs, start_positions=start_positions, end_positions=end_positions)
loss = outputs.loss
start_scores = outputs.start_logits
end_scores = outputs.end_logits

这将返回开始和结束分数，但我怎样才能从这里获得有意义的文本答案？

Answer 1

所以我做了一点挖掘，看起来分数可以转换为可用于构建答案的标记。 这是一个简短的例子：

answer_start = torch.argmax(start_scores) 
answer_end = torch.argmax(end_scores) + 1

tokenizer.convert_tokens_to_string(tokenizer.convert_ids_to_tokens(inputs["input_ids"][0][answer_start:answer_end]))