sz128/pretrained_word_embeddings

It is about how to load and aggregate pretrained word embeddings in pytorch, e.g., ELMo\BERT\XLNET.

27
/ 100
Experimental

When performing natural language processing tasks, this helps you retrieve meaningful numerical representations (word embeddings) for words in your text. It takes raw text and pre-trained language models like ELMo, BERT, or XLNet as input, and outputs aggregated word embeddings suitable for further analysis. This is for machine learning engineers and data scientists working on text-based applications.

No commits in the last 6 months.

Use this if you need to transform text into high-quality word embeddings using popular pre-trained models and require flexible methods for combining token-level embeddings back into word-level representations.

Not ideal if you are not comfortable with Python and PyTorch, or if you primarily work with other deep learning frameworks.

natural-language-processing text-analytics deep-learning data-science machine-learning-engineering
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 14 / 25

How are scores calculated?

Stars

12

Forks

3

Language

Python

License

Last pushed

Mar 02, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/sz128/pretrained_word_embeddings"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.