如何使用 FastText 查找相似的单词? [英] How to find similar words with FastText?

问题描述

我正在玩 FastText，https://pypi.python.org/pypi/fasttext，与 Word2Vec 非常相似.由于它似乎是一个相当新的库，还没有多少内置函数，我想知道如何提取形态相似的词.

I am playing around with FastText, https://pypi.python.org/pypi/fasttext,which is quite similar to Word2Vec. Since it seems to be a pretty new library with not to many built in functions yet, I was wondering how to extract morphological similar words.

例如:model.similar_word("dog") -> 狗.但是没有内置函数.

For eg: model.similar_word("dog") -> dogs. But there is no function built-in.

如果我输入model["dog"]

我只得到了可能用于比较余弦相似度的向量.model.cosine_similarity(model["dog"], model["dogs"]]).

I only get the vector, that might be used to compare cosine similarity. model.cosine_similarity(model["dog"], model["dogs"]]).

我是否必须进行某种循环并对文本中的所有可能对执行 cosine_similarity ?这需要时间......!!!

Do I have to make some sort of loop and do cosine_similarity on all possible pairs in a text? That would take time ...!!!

推荐答案

使用 Gensim，使用 load.word2vec 模型加载 fastText 训练好的 .vec 文件，并使用 most_similiar() 方法查找相似词！

Use Gensim, load fastText trained .vec file with load.word2vec models and use most_similiar() method to find similar words!

这篇关于如何使用 FastText 查找相似的单词?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！