一种方法是使用两个单独的嵌入,一个用于预训练,另一个用于待训练.

GloVe应该被冻结,而没有预训练表示的GloVe应该从可训练层获取.

如果格式化数据以用于预训练的令牌表示,则该数据的范围比不具有GloVe表示的令牌的范围小.假设您的预训练索引在[0,300]范围内,而没有代表性的索引在[301,500].我会遵循以下思路：

import numpy as np
import torch


class YourNetwork(torch.nn.Module):
    def __init__(self,glove_embeddings: np.array,how_many_tokens_not_present: int):
        self.pretrained_embedding = torch.nn.Embedding.from_pretrained(glove_embeddings)
        self.trainable_embedding = torch.nn.Embedding(
            how_many_tokens_not_present,glove_embeddings.shape[1]
        )
        # Rest of your network setup

    def forward(self,batch):
        # Which tokens in batch do not have representation,should have indices BIGGER
        # than the pretrained ones,adjust your data creating function accordingly
        mask = batch > self.pretrained_embedding.shape[0]

        # You may want to optimize it,you could probably get away without copy,though
        # I'm not currently sure how
        pretrained_batch = batch.copy()
        pretrained_batch[mask] = 0

        embedded_batch = self.pretrained_embedding[pretrained_batch]

        # Every token without representation has to be brought into appropriate range
        batch -= self.pretrained_embedding.shape[0]
        # Zero out the ones which already have pretrained embedding
        batch[~mask] = 0
        non_pretrained_embedded_batch = self.trainable_embedding(batch)

        # And finally change appropriate tokens from placeholder embedding created by
        # pretrained into trainable embeddings.
        embedded_batch[mask] = non_pretrained_embedded_batch[mask]

        # Rest of your code
        ...

假设您的预训练索引在[0,500].

2.指定令牌的零梯度.

这有点棘手,但我认为它非常简洁且易于实现.因此,如果获得没有GloVe表示形式的标记的索引,则可以在反向传播后将它们的梯度显式归零,这样这些行就不会被更新.

import torch

embedding = torch.nn.Embedding(10,3)
X = torch.LongTensor([[1,2,4,5],[4,3,9]])

values = embedding(X)
loss = values.mean()

# Use whatever loss you want
loss.backward()

# Let's say those indices in your embedding are pretrained (have GloVe representation)
indices = torch.LongTensor([2,5])

print("Before zeroing out gradient")
print(embedding.weight.grad)

print("After zeroing out gradient")
embedding.weight.grad[indices] = 0
print(embedding.weight.grad)

和第二种方法的输出：

Before zeroing out gradient
tensor([[0.0000,0.0000,0.0000],[0.0417,0.0417,0.0417],[0.0833,0.0833,0.0833],[0.0000,0.0417]])
After zeroing out gradient
tensor([[0.0000,0.0417]])