BERT - LIME (binary text classification)

[loukasilias]

I am trying to use LIME with a model consisting of BERT --> Pooling layer --> Dense (128 units) --> Dense (1 unit, sigmoid activation function). This is a binary classification code.

I have implemented the model as follows:

class MyModel(tf.keras.Model):

    def __init__(self, flag):

        super(MyModel,self).__init__()
        self.bert_model = TFBertModel.from_pretrained("bert-base-uncased")
        self.bert_model.trainable = flag
        self.layer_3 = Dense(units = 128, activation = 'relu')
        self.layer_4 = Dense(units = 1, activation = 'sigmoid')
        self.pooling = tf.keras.layers.GlobalMaxPool1D()

    def call(self,inputs):
        output_sentence_1 = self.bert_model(input_ids = inputs[0], attention_mask = inputs[1])
        output_sentence_1 = self.pooling(output_sentence_1['last_hidden_state'])
        layer_output = self.layer_3(output_sentence_1)
        output = self.layer_4(layer_output)

        return output

I am trying to use LIME as follows:

from lime.lime_text import LimeTextExplainer
explainer = LimeTextExplainer(class_names = ['truthful', 'deceptive'])
tokenizer = BertTokenizer.from_pretrained("bert-base-uncased", do_lower_case=True)

def predict_probab(STR):

    list_all = []
    for strings in STR:
        z = tokenizer.encode_plus(strings, add_special_tokens = True, max_length = 512, truncation = True,padding = 'max_length', return_token_type_ids=True, return_attention_mask = True,  return_tensors = 'np')
        inputs = [z['input_ids'], z['attention_mask']]
        k = []
        k.append(float(model.predict(inputs).reshape(-1,1)))
        k.append(float(1-model.predict(inputs).reshape(-1,1)))
        k = np.array(k).reshape(1,-1)
        list_all.append(k)
    list_all = np.array(list_all).squeeze()
    return np.array(list_all)

STR = []
for strings in X_test[:10]:
    STR.append(str(strings))

exp = explainer.explain_instance(str(STR[0]), predict_probab, num_features=100, num_samples=150)

I would like to ask you if the methodology of LIME is correct.

[beyondguo]

？？？ what is your problem