How to calculate the distance in the meaning of two words in Python

Question

I am wondering if it is possible to calculate the distance / similarity between two related words in Python (for example, “fraud” and “theft”). These two words are not synonyms per se, but they are clearly related. Are there any concepts / algorithms in NLP that can show this ratio numerically? Maybe through NLTK?

I am not looking for the Levenshtein distance, which refers to the individual characters that make up the word. I am looking for how it matters.

Would thank for the help provided.

Answer 1

My suggestion is as follows:

• , .
• .
• .

:

• .
• .

!...

• , .
• n (= 5 ) , .
• , .
• .
• .
• .

Answer 2

, Word2Vec, FastText ..

gensim - Python, .