如何将单词和向量手动添加到 Word2vec gensim? [英] How to add words and vectors manually to Word2vec gensim?

问题描述

比方说，word2vec.model 是我经过训练的 word2vec 模型.当出现词汇外单词 (oov_word) 时，我使用 compute_vec(oov_word) 方法计算向量 vec.现在，我想将 oov_word 及其相应的向量 vec 添加/附加到我已经训练好的模型 word2vec.model.

Let's say, word2vec.model is my trained word2vec model. When a out-of-vocabulary word (oov_word) occurs, I compute a vector vec using compute_vec(oov_word) method. Now, I want to add/append oov_word and its corresponding vector vec to my already trained model word2vec.model.

我已经检查了以下链接.但他们没有回答我的问题.

I have already checked the below links. But they do not answer my question.

组合/添加来自不同 word2vec 模型的向量

https://datascience.stackexchange.com/questions/49431/how-to-train-an-existing-word2vec-gensim-model-on-new-words

https://radimrehurek.com/gensim/models/keyedvectors.html#gensim.models.keyedvectors.BaseKeyedVectors.add

推荐答案

from gensim.models.keyedvectors import WordEmbeddingsKeyedVectors
vector_length = 100
kv = WordEmbeddingsKeyedVectors(vector_length)

# wordList - list of words
# vectorList - list of the vector corresponding to the words

kv.add(wordList, vectorList)

kv.most_similar(word1) # gives the list of words similar to word1

这篇关于如何将单词和向量手动添加到 Word2vec gensim?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！