# PubMed word vectors

**URL:** <https://support.prodi.gy/t/pubmed-word-vectors/4660>\
**Category:** Uncategorized\
**Tags:** textcat, custom, solved, medical\
**Created:** [September 7, 2021, 1:10am UTC](https://support.prodi.gy/t/pubmed-word-vectors/4660 "2021-09-07T01:10:00Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![beperron](https://sea2.discourse-cdn.com/flex020/user_avatar/support.prodi.gy/beperron/32/1878_2.png) [@beperron](https://support.prodi.gy/u/beperron)\
**Post date:** [September 7, 2021, 1:10am UTC](https://support.prodi.gy/t/pubmed-word-vectors/4660/1 "2021-09-07T01:10:00Z")

</div>

I am using Prodigy to build a model that classifies the scholarly literature on COVID. My initial task is quite straightforward -- to separate empirical publications (i.e., actual science) from non-empirical publications (e.g., personal essays, position papers, critiques). My collection is around ~275k, so this is definitely an NLP task. I'm really impressed with the results, so far -- and, of course, the software!

Here is my question: I'm using the `en_core_web_lg` word vectors in the model. I would actually like to try using the word vectors trained on the PubMed research, which I can obtain here:

[https://bio.nlplab.org/](https://bio.nlplab.org/)

Here is the file manifest:

 ![Screen Shot 2021-09-06 at 8.52.17 PM](https://us1.discourse-cdn.com/flex020/uploads/prodigy/original/2X/7/7f50020f37441074efcf6973094014a34f32c40a.png)

I'm interested in trying any of the .bin models, but am not having luck getting them into my model. Is there any special configurations I need to do after obtaining these files? These are Word2Vec models. Is there some documentation I missed?

Thanks,  
Brian

---

<div class="post-metadata">

**Author:** ![ines](https://sea2.discourse-cdn.com/flex020/user_avatar/support.prodi.gy/ines/32/3_2.png) [@ines](https://support.prodi.gy/u/ines)\
**Post date:** [September 7, 2021, 2:47am UTC](https://support.prodi.gy/t/pubmed-word-vectors/4660/2 "2021-09-07T02:47:51Z")

</div>

Hi and thanks 😊 If the vectors are word2vec vectors, you can import them into spaCy using the [`init vectors`](https://spacy.io/api/cli#init-vectors) command, which outputs a loadable spaCy model that you can use instead of `en_core_web_lg`. See here for details: [https://spacy.io/usage/linguistic-features#adding-vectors](https://spacy.io/usage/linguistic-features#adding-vectors)

Btw, just in case you haven't seen it, you might also find some of the scispaCy pipelines useful: [scispacy | SpaCy models for biomedical text processing](https://allenai.github.io/scispacy/) If I read the docs correctly, the included word vectors may even be the same vectors you want to use!

---

<div class="post-metadata">

**Author:** ![beperron](https://sea2.discourse-cdn.com/flex020/user_avatar/support.prodi.gy/beperron/32/1878_2.png) [@beperron](https://support.prodi.gy/u/beperron)\
**Post date:** [September 7, 2021, 2:22pm UTC](https://support.prodi.gy/t/pubmed-word-vectors/4660/3 "2021-09-07T14:22:04Z")

</div>

Thanks so much! Is there a straightforward way to use the `scispacy` models with Progidy? I installed the package and immediately got Traceback errors. Upon installation, `scispacy` detected and replaced `spacy` with an incompatible version. So, then I downloaded the model directly, unzipped and then called the model from the path, as such:

`OSError: [E053] Could not read config.cfg from en_core_sci_scibert-0.4.0/config.cfg`

My directory is set up as follows:  
 ![Screen Shot 2021-09-07 at 10.17.04 AM](https://us1.discourse-cdn.com/flex020/uploads/prodigy/original/2X/7/7536cd34f9e363285cd73dbc3c2d57cf8212c728.png)

Do you have a short answer on whether there is a quick an easy way to the `scispacy` models within Prodigy? I am a Python newbie, but I have very good support with my university and can work with them if there is a solution.

Thanks again!  
Brian

---

<div class="post-metadata">

**Author:** ![ines](https://sea2.discourse-cdn.com/flex020/user_avatar/support.prodi.gy/ines/32/3_2.png) [@ines](https://support.prodi.gy/u/ines)\
**Post date:** [September 8, 2021, 3:49am UTC](https://support.prodi.gy/t/pubmed-word-vectors/4660/4 "2021-09-08T03:49:24Z")

</div>

> [@beperron](#):
>
> So, then I downloaded the model directly, unzipped and then called the model from the path, as such:

I think the problem is that you're trying to load the top-level package directory. If you've unzipped the model, you want to be loading the model data directory inside it (the one that includes the `config.cfg`).

Btw, the pipelines shipped by scispaCy are Python packages that you can install via `pip install` so you should be able to just run the following to install them in your environment (without unzipping!):

```bash
pip install en_core_sci_scibert-0.4.0.tar.gz

```

You can then load the pipeline in spaCy as `nlp = spacy.load("en_core_sci_scibert")`.