Keras:用于嵌入/向量的附加层? [英] Keras : addition layer for embeddings / vectors?

问题描述

我有3个单词嵌入物:

• 嵌入#1:[w11，w12，w13，w14]
• 嵌入#2:[w21，w22，w23，w24]
• 嵌入#3:[w31，w32，w33，w34]

是否有一种方法可以通过将所有三个向量相加，并同时使用所有向量的可训练权重来进行第四次嵌入，例如:

Is there a way to get a fourth embedding by adding all three vectors, with the trainable weights from all of them, like:

• 嵌入#4:[w11 + w21 + w31，w12 + w22 + w32，w13 + w23 + w33，w14 + w24 + w34]

?有没有办法在keras层中做到这一点?

? Is there a way to do this in a keras layer?

问题
我想学习印尼语的词嵌入.我计划通过使用LSTM训练序列预测机来做到这一点.

Problem
I want to learn the word embeddings for Indonesian language. I plan to do this by training a sequence prediction machine using LSTMs.

但是，印尼语的语法不同于英语.特别是在印尼语中，您可以使用前缀和后缀来修改单词.名词词加上前缀可以变成动词，而后缀则变成形容词.您可以在一个单词中放入这么多单词，以便单个基本单词可以有5个或更多的变体.

However, the grammar of Indonesian language is different from english. Especially, in Indonesian, you can modify a word using prefixes and suffixes. A noun word when given a prefix can become a verb, and when given a suffix can become an adjective. You can put so many into one word, so that a single base word can have 5 or more variations.

例如:

1. tani的意思是农场(动词)
2. pe-tani是农民
3. 每tani-an表示农场(名词)
4. ber-tani的意思是农场(动词，含义略有不同)

通过在单词之间添加前缀来完成的语义转换在单词之间是一致的.例如:

The transformation of semantic done by appending a prefix to a word is consistent between words. For example :

1. pe-tani对tani来说是pe-layan对莱昂，什么pe-layar对莱昂，什么pe-tembak对Tembak，依此类推.
每个人对主要人而言，每个人对上师而言是什么，对基拉人而言对基拉来说是什么，对苏拉人而言对苏拉特来说是什么，依此类推.

1. pe-tani is to tani is what pe-layan is to layan, what pe-layar is to layar, what pe-tembak is to tembak, and so on.
2. per-main-an is to main is what per-guru-an is to guru, what per-kira-an is to kira, what per-surat-an is to surat, and so on.

因此，我计划将前缀和后缀表示为嵌入，这将用于对基本单词的嵌入进行添加，从而产生新的嵌入.因此，复合词的含义是从基本词和词缀的嵌入中得出的，而不是存储为单独的嵌入.但是我不知道如何在Keras层中执行此操作.如果以前曾有人问过，我找不到它.

Therefore, i plan to represent the prefixes and suffixes as embeddings, which would be used to do an addition to the base word's embedding, producing a new embedding. So the meaning of the composite word is derived from the embeddings of the base word and the affixes, not stored as a separate embeddings. However i don't know how to do this in a Keras layer. If it had been asked before, i cannot find it.

推荐答案

当您说三个单词嵌入"时，我看到三个嵌入层，例如:

When you say "three word embeddings", I see three Embedding layers, such as:

input1 = Input((sentenceLength,))
input2 = Input((sentenceLength,))
input3 = Input((sentenceLength,))

emb1 = Embedding(...options...)(input1)
emb2 = Embedding(...options...)(input2)
emb3 = Embedding(...options...)(input3)

您可以使用简单的Add()层对这三个层求和:

You can use a simple Add() layer to sum the three:

summed = Add()([emb1,emb2,emb3])

然后您继续建模...

Then you continue your modeling...

#after creating the rest of the layers and getting the desired output:
model = Model([input1,input2,input3],output)

---

如果您不使用嵌入层，但是要输入三个向量:

---

If you're not using embedding layers, but you're inputting three vectors:

input1 = Input((4,)) #or perhaps (sentenceLength,4)
input2 = Input((4,))
input3 = Input((4,))

added = Add()([input1,input2,input3])

其余的都一样.

如果这不是您的问题，请提供三个单词嵌入"的来源，打算如何选择它们的详细信息，等等.

If this is not your question, please give more details about where the three "word embeddings" are coming from, how you intend to select them, etc.

这篇关于Keras:用于嵌入/向量的附加层?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！