transformers-interpret is a good toolkit, but I want to know more about the algorithm involved in transformers-interpret. I'm curious about the method SequenceClassificationExplainer, this method directly calls captum.attr.visualization. But I want to know more about the algorithm involved in visualize text, what algorithms used to visualize text?
transformers-interpret is a good toolkit, but I want to know more about the algorithm involved in transformers-interpret. I'm curious about the method SequenceClassificationExplainer, this method directly calls captum.attr.visualization. But I want to know more about the algorithm involved in visualize text, what algorithms used to visualize text?