使用双向LSTM训练词向量的代码

以下是使用双向LSTM训练词向量的Python代码示例：

import tensorflow as tf
from tensorflow.keras.layers import Input, Embedding, Bidirectional, LSTM, Dense
from tensorflow.keras.models import Model
from tensorflow.keras.preprocessing.text import Tokenizer
from tensorflow.keras.preprocessing.sequence import pad_sequences

# 构建模型
def build_model(vocab_size, embedding_dim, lstm_units):
    inputs = Input(shape=(None,))
    x = Embedding(vocab_size, embedding_dim)(inputs)
    x = Bidirectional(LSTM(lstm_units))(x)
    outputs = Dense(embedding_dim, activation='linear')(x)
    model = Model(inputs=inputs, outputs=outputs)
    return model

# 训练词向量
def train_word_embeddings(texts, embedding_dim=100, lstm_units=128, batch_size=64, epochs=10):
    # 构建 Tokenizer
    tokenizer = Tokenizer()
    tokenizer.fit_on_texts(texts)

    # 构建训练数据
    sequences = tokenizer.texts_to_sequences(texts)
    padded_sequences = pad_sequences(sequences)

    # 构建模型
    model = build_model(len(tokenizer.word_index) + 1, embedding_dim, lstm_units)
    model.compile(loss='mse', optimizer='adam')

    # 训练模型
    model.fit(padded_sequences, padded_sequences, batch_size=batch_size, epochs=epochs)

    # 获取词向量
    embeddings = model.layers[1].get_weights()[0]
    word_index = tokenizer.word_index
    word_embeddings = {word: embeddings[idx] for word, idx in word_index.items()}

    return word_embeddings

使用方法：

texts = ['I like to eat apple', 'He hates to eat banana', 'She loves to eat orange']
word_embeddings = train_word_embeddings(texts)

其中`texts`为训练文本，`word_embeddings`为训练得到的词向量。