News for hackers. Stuff that matters.

A comment on Show HN: Word2vec Algorithm in ~100sloc with NumPy.

Re:Show HN: Word2vec Algorithm in ~100sloc with NumPy by sireat on Thursday June 01, 2023 @12:56PM (#36153981)
The golden standard for word2vec and topic modeling in general is gensim: https://radimrehurek.com/gensim/models/word2vec.html

I've been using gensim for a few years for topic modeling. It works great with pyLDAvis for visualizations.

How does your implementation differ from the one by Radim?

[ Parent | on HN ]
Re:Show HN: Word2vec Algorithm in ~100sloc with NumPy by extasia on Saturday June 03, 2023 @07:03AM (#36175564)
It's not a serious implementation but one for didactic purposes:)

I've used gensim's one and it seems great for practical use but I wanted to build an understanding of the underlying algorithm, so built my own from scratch. I was hoping others might learn from it, but it's not really a practical approach to constructing w2v embeddings.

[ Parent | on HN ]