awslabs/sagemaker-privacy-for-nlp
A solution that helps apply a privacy preserving mechanism to NLP data, using Amazon SageMaker.
This solution helps organizations responsibly build and deploy Natural Language Processing (NLP) models, such as those for sentiment analysis or chatbots, using sensitive user text data. It takes your raw text data and applies a privacy-preserving mechanism to produce a 'privatized' version. Data scientists or machine learning engineers in charge of developing ethical AI systems for their company would use this.
No commits in the last 6 months.
Use this if you need to train NLP models on text data that contains sensitive user information and want to protect individual privacy while still achieving business goals.
Not ideal if your data is not text-based, or if your primary concern is not user privacy in the context of NLP model training.
Stars
18
Forks
6
Language
Jupyter Notebook
License
—
Category
Last pushed
May 30, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/awslabs/sagemaker-privacy-for-nlp"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
dselivanov/text2vec
Fast vectorization, topic modeling, distances and GloVe word embeddings in R.
vzhong/embeddings
Fast, DB Backed pretrained word embeddings for natural language processing.
dccuchile/spanish-word-embeddings
Spanish word embeddings computed with different methods and from different corpora
ncbi-nlp/BioSentVec
BioWordVec & BioSentVec: pre-trained embeddings for biomedical words and sentences
avidale/compress-fasttext
Tools for shrinking fastText models (in gensim format)