# Doc2Vec in Julia

**URL:** <https://discourse.julialang.org/t/doc2vec-in-julia/78907>\
**Category:** Machine Learning\
**Tags:** flux, machine-learning, nlp\
**Created:** [April 2, 2022, 9:34am UTC](https://discourse.julialang.org/t/doc2vec-in-julia/78907 "2022-04-02T09:34:17Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![Salvatore\_Cosentino](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/salvatore_cosentino/32/15418_2.png) [@Salvatore\_Cosentino](https://discourse.julialang.org/u/Salvatore_Cosentino)\
**Post date:** [April 2, 2022, 9:34am UTC](https://discourse.julialang.org/t/doc2vec-in-julia/78907/1 "2022-04-02T09:34:17Z")

</div>

Hello everybody.

I would like one of students to start learning Julia and move from Python.  
The project is working on uses `Gensim` module for Python, which allows for modelling semantic NLP problems.  
Specifically he is using `Doc2Vec` (aka Paragraph to vector) to generate embeddings of phrases.  
I know that there are some implementations of `Word2Vec` (on which Doc2Vec is based) but I could not find much regarding `Doc2Vec`.

Does any of you know any implementation of Doc2Vec (e.g., in ‘’‘Flux’')?

I really ❤ Julia and would like some of my students to like it too 😄

Thanks a lot in advance for your kind help.

---

<div class="post-metadata">

**Author:** ![ToucheSir](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/touchesir/32/14411_2.png) [@ToucheSir](https://discourse.julialang.org/u/ToucheSir)\
**Post date:** [April 2, 2022, 5:12pm UTC](https://discourse.julialang.org/t/doc2vec-in-julia/78907/2 "2022-04-02T17:12:40Z")

</div>

It appears [https://github.com/JuliaText/Embeddings.jl](https://github.com/JuliaText/Embeddings.jl) only has Word2Vec and not document vectors. If you’re willing to branch out a little more, [https://github.com/chengchingwen/Transformers.jl/](https://github.com/chengchingwen/Transformers.jl/) allows access to a larger range of embedding generators from more sophisticated/recent language models.

---

<div class="post-metadata">

**Author:** ![Salvatore\_Cosentino](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/salvatore_cosentino/32/15418_2.png) [@Salvatore\_Cosentino](https://discourse.julialang.org/u/Salvatore_Cosentino)\
**Post date:** [April 4, 2022, 3:42am UTC](https://discourse.julialang.org/t/doc2vec-in-julia/78907/3 "2022-04-04T03:42:57Z")

</div>

Thanks a lot for your message.  
Might take a look at transformers, although for my application it would be an overkill…