如何获取 Huggingface Transformer 模型预测 [零样本分类] 的 SHAP 值？

Question

通过 Huggingface 给出零样本分类任务，如下所示：

from transformers import pipeline
classifier = pipeline("zero-shot-classification", model="facebook/bart-large-mnli")

example_text = "This is an example text about snowflakes in the summer"
labels = ["weather", "sports", "computer industry"]
        
output = classifier(example_text, labels, multi_label=True)
output 
{'sequence': 'This is an example text about snowflakes in the summer',
'labels': ['weather', 'sports'],
'scores': [0.9780895709991455, 0.021910419687628746]}

我正在尝试提取 SHAP 值以生成基于文本的预测结果解释，如下所示：SHAP for Transformers

我已经根据上面的网址尝试了以下操作：

from transformers import AutoModelForSequenceClassification, AutoTokenizer, ZeroShotClassificationPipeline

model = AutoModelForSequenceClassification.from_pretrained('facebook/bart-large-mnli')
tokenizer = AutoTokenizer.from_pretrained('facebook/bart-large-mnli')

pipe = ZeroShotClassificationPipeline(model=model, tokenizer=tokenizer, return_all_scores=True)

def score_and_visualize(text):
    prediction = pipe([text])
    print(prediction[0])

    explainer = shap.Explainer(pipe)
    shap_values = explainer([text])

    shap.plots.text(shap_values)

score_and_visualize(example_text)

有什么建议么？提前感谢您的帮助！

除了上述管道之外，以下管道也可以工作：

from transformers import AutoModelForSequenceClassification, AutoTokenizer, ZeroShotClassificationPipeline

model = AutoModelForSequenceClassification.from_pretrained('facebook/bart-large-mnli')
tokenizer = AutoTokenizer.from_pretrained('facebook/bart-large-mnli')

classifier = ZeroShotClassificationPipeline(model=model, tokenizer=tokenizer, return_all_scores=True)

example_text = "This is an example text about snowflakes in the summer"
labels = ["weather", "sports"]

output = classifier(example_text, labels)
output 
{'sequence': 'This is an example text about snowflakes in the summer',
'labels': ['weather', 'sports'],
'scores': [0.9780895709991455, 0.021910419687628746]}

Answer 1

shap目前不支持ZeroShotClassificationPipeline ，但您可以使用解决方法。需要解决方法是因为：

1. shap Expander 仅向模型转发一个参数（本例中为管道），但 ZeroShotClassificationPipeline 需要两个参数，即文本和标签。
2. shapExplainer 将访问模型的配置并使用它的label2id和id2label属性。它们与从 ZeroShotClassificationPipeline 返回的标签不匹配，将导致错误。

以下是一种可能的解决方法的建议。我建议在shap上提出问题并请求对 Huggingface 的 ZeroShotClassificationPipeline 的官方支持。

import shap
from transformers import AutoModelForSequenceClassification, AutoTokenizer, ZeroShotClassificationPipeline
from typing import Union, List

weights = "valhalla/distilbart-mnli-12-3"

model = AutoModelForSequenceClassification.from_pretrained(weights)
tokenizer = AutoTokenizer.from_pretrained(weights)

# Create your own pipeline that only requires the text parameter 
# for the __call__ method and provides a method to set the labels
class MyZeroShotClassificationPipeline(ZeroShotClassificationPipeline):
    # Overwrite the __call__ method
    def __call__(self, *args):
      o = super().__call__(args[0], self.workaround_labels)[0]

      return [[{"label":x[0], "score": x[1]}  for x in zip(o["labels"], o["scores"])]]

    def set_labels_workaround(self, labels: Union[str,List[str]]):
      self.workaround_labels = labels

example_text = "This is an example text about snowflakes in the summer"
labels = ["weather","sports"]

# In the following, we address issue 2.
model.config.label2id.update({v:k for k,v in enumerate(labels)})
model.config.id2label.update({k:v for k,v in enumerate(labels)})

pipe = MyZeroShotClassificationPipeline(model=model, tokenizer=tokenizer, return_all_scores=True)
pipe.set_labels_workaround(labels)

def score_and_visualize(text):
    prediction = pipe([text])
    print(prediction[0])

    explainer = shap.Explainer(pipe)
    shap_values = explainer([text])

    shap.plots.text(shap_values)


score_and_visualize(example_text)

输出：