[英]How to load pre-trained model with in gensim and train doc2vec with it?
I am having a ready to go word2vec model that I already trained.我准备好了我已经训练过的 word2vec 模型。 I have serialized it as a CSV file:我已将其序列化为 CSV 文件:
word, v0, v1, ..., vN
house, 0.1234, 0.4567, ..., 0.3461
car, 0.456, 0.677, ..., 0.3461
What I'd like to know is how I can load that word vector model in gensim
and use that to train a paragraph or doc2vec model.我想知道的是如何在gensim
加载该词向量模型并使用它来训练段落或 doc2vec 模型。
This Doc2Vec tutorial says I can load a model in form of a " # C text format
" but I have no idea what that actually means.这个Doc2Vec 教程说我可以以“ #C # C text format
”的形式加载模型,但我不知道这实际上意味着什么。 What is "C text format" in the first place but more important:什么是“C 文本格式”,但更重要的是:
How do I build the vocabulary from my word2vec model?如何从我的 word2vec 模型构建词汇表?
Doc2Vec does not need word-vectors as an input: it will create any word-vectors that are needed during its own training. Doc2Vec 不需要词向量作为输入:它将创建在其自身训练期间需要的任何词向量。 (And some modes, like pure DBOW – dm=0, dbow_words=0
– don't use or train word-vectors at all.) (还有一些模式,比如纯 DBOW—— dm=0, dbow_words=0
根本不使用或训练词向量。)
Seeding a Doc2Vec model with word-vectors might help or hurt;用词向量播种 Doc2Vec 模型可能会有所帮助或有害; there's not much theory or published results to offer guidance.没有太多理论或已发表的结果可以提供指导。 There's an experimental method on Word2Vec, intersect_word2vec_format()
, that can merge word2vec-c-format vectors into a model with an existing vocabulary, but you'd need to review the source to really understand its assumptions: Word2Vec 有一种实验方法intersect_word2vec_format()
,可以将 word2vec-c-format 向量合并到具有现有词汇表的模型中,但您需要查看源代码才能真正理解其假设:
https://github.com/RaRe-Technologies/gensim/blob/51753b95415bbc344ea6af671818277464905ea2/gensim/models/word2vec.py#L1140 https://github.com/RaRe-Technologies/gensim/blob/51753b95415bbc344ea6af671818277464905ea2/gensim/models/word2vec.py#L1140
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.