Deep learning 迪帕夫洛夫对自己的反应进行了排名

Deep learning 迪帕夫洛夫对自己的反应进行了排名,deep-learning,nlp,search-engine,deeppavlov,Deep Learning,Nlp,Search Engine,Deeppavlov,有人知道如何使用deeppavlov排名模块并给出自己的答案吗?文档()提供了以下代码(用于保险数据集): 但当我在ubuntu数据集上使用这段代码时: rank_model = build_model(configs.ranking.ranking_ubuntu_v2_bert_sep_interact, download=False) predictor = rank_model.pipe[-1][-1] candidates = ['environment variable', 'grap

有人知道如何使用deeppavlov排名模块并给出自己的答案吗?文档()提供了以下代码(用于保险数据集):

但当我在ubuntu数据集上使用这段代码时:

rank_model = build_model(configs.ranking.ranking_ubuntu_v2_bert_sep_interact, download=False)
predictor = rank_model.pipe[-1][-1]
candidates = ['environment variable', 'graphical interface', 'broken terminal']
predictor.rebuilt_responces(candidates)
事实证明,没有重建响应的
方法:

AttributeError                            Traceback (most recent call last)
<ipython-input-9-e013af513ae2> in <module>
      4 predictor = rank_model.pipe[-1][-1]
      5 candidates = ['environment variable', 'graphical interface', 'broken terminal']
----> 6 predictor.rebuilt_responces(candidates)

AttributeError: 'BertSepRankerPredictor' object has no attribute 'rebuilt_responces'
AttributeError回溯(最近一次调用)
在里面
4预测值=秩_模型管道[-1][-1]
5个候选项=['环境变量','图形界面','断开的终端']
---->6预测者。重建的反应(候选者)
AttributeError:'BertSepRankerPredictor'对象没有属性'Rebuilded\u responces'

有什么想法吗?

我不得不用数据手动替换文件。github问题中提供了解决方案:

AttributeError                            Traceback (most recent call last)
<ipython-input-9-e013af513ae2> in <module>
      4 predictor = rank_model.pipe[-1][-1]
      5 candidates = ['environment variable', 'graphical interface', 'broken terminal']
----> 6 predictor.rebuilt_responces(candidates)

AttributeError: 'BertSepRankerPredictor' object has no attribute 'rebuilt_responces'