使用 LSTM 微调通用句子编码器

Fine-tuning Universal Sentence Encoder with LSTM

输入数据:

string_1_A, string_2_A, string_3_A, label_A
string_1_B, string_2_B, string_3_B, label_B
...
string_1_Z, string_2_Z, string_3_Z, label_Z

我想使用 Universal Sentence Encoder (v4) 来嵌入该字符串(将是句子),然后将其输入 LSTM 以对该序列进行预测。我最终得到以下代码:

import tensorflow_hub as hub
import tensorflow as tf
import tensorflow.keras.backend as K
from tensorflow.keras.layers import LSTM


module_url = "../resources/embeddings/use-4"

def get_lstm_model():
    embedding_layer = hub.KerasLayer(module_url)

    inputs = tf.keras.layers.Input(shape=(3, ), dtype=tf.string)
    x = tf.keras.layers.Lambda(lambda y: tf.expand_dims(embedding_layer(tf.squeeze(y)), 1))(inputs)
    x = LSTM(128, return_sequences=False)(x)
    outputs = tf.keras.layers.Dense(1, activation="sigmoid")(x)

    model = tf.keras.Model(inputs=inputs, outputs=outputs)
    model.compile("adam",  K.binary_crossentropy)
    model.summary()
    return model


if __name__ == '__main__':
    model = get_lstm_model()
    print(model.predict([[["a"], ["b"], ["c"]]]))

问题是某些层的 input/output 维度与我预期的不匹配(而不是我期望的 1 3):

input_1 (InputLayer)         [(None, 3)]               0         
_________________________________________________________________
lambda (Lambda)              (None, ***1***, 512)            0       

任何建议 - 我认为我需要更好地处理挤压和取消挤压。

最简单的解决方案是将每个 string/sentence 分别 传递给通用句子编码器。这会为形状为 512 的每个 string/sentence 生成一个嵌入,可以将其连接起来形成形状为 (None、n_sentences、512) 的张量。

这是模型的代码:

n_sentences = 50
module_url = "https://tfhub.dev/google/universal-sentence-encoder/4"

def get_lstm_model():
    embedding_layer = hub.KerasLayer(module_url, trainable=True)

    input = Input(shape=(n_sentences,), dtype=tf.string)
    x = [Reshape((1,512))(embedding_layer(input[:, s])) for s in range(n_sentences)]
    x = Concatenate(axis=1)(x)
    x = LSTM(128, return_sequences=False)(x)
    output = Dense(1, activation="sigmoid")(x)

    model = Model(inputs=input, outputs=output)
    model.compile("adam", "binary_crossentropy")
    model.summary()
    return model

推理时:

sentences = [str(i) for i in range(n_sentences)]
X = [sentences] # 1 sample
print(model.predict(X).shape)

X = [sentences, sentences[::-1]] # 2 samples
print(model.predict(X).shape)

Here 运行 笔记本