cbaziotis/neat-vision
Neat (Neural Attention) Vision, is a visualization tool for the attention mechanisms of deep-learning models for Natural Language Processing (NLP) tasks. (framework-agnostic)
This tool helps NLP practitioners understand why their deep-learning models make specific predictions on text data. You input JSON files containing tokenized text, attention scores, and model predictions (like regression values or classification probabilities). It then outputs interactive visualizations that show how different words in a sentence contribute to the model's decision, making it easier to debug and explain model behavior. This is ideal for researchers, data scientists, or NLP engineers who build and evaluate text-based AI models.
251 stars. No commits in the last 6 months.
Use this if you need to visualize the attention mechanisms and predictions of your sentence-level NLP models for tasks like classification or regression.
Not ideal if you need to visualize attention for document-level or sequence-to-sequence models, or if you are not working with deep-learning NLP models.
Stars
251
Forks
24
Language
Vue
License
MIT
Category
Last pushed
May 04, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/cbaziotis/neat-vision"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
philipperemy/keras-attention
Keras Attention Layer (Luong and Bahdanau scores).
tatp22/linformer-pytorch
My take on a practical implementation of Linformer for Pytorch.
datalogue/keras-attention
Visualizing RNNs using the attention mechanism
ematvey/hierarchical-attention-networks
Document classification with Hierarchical Attention Networks in TensorFlow. WARNING: project is...
thushv89/attention_keras
Keras Layer implementation of Attention for Sequential models