yufengm/SelfAttentive
Implementation of A Structured Self-attentive Sentence Embedding
This project helps you understand which words in customer reviews or text feedback contribute most to its overall sentiment or classification. You input raw text reviews and it outputs a classification (like 'helpful' or 'not helpful') along with visualizations that highlight the key words driving that decision. It's designed for data scientists or researchers who need to interpret and explain text classifications.
108 stars. No commits in the last 6 months.
Use this if you need to classify text and also explain *why* it was classified that way, by identifying the most influential words.
Not ideal if you're looking for an out-of-the-box solution for text classification without needing to delve into model training or interpretation.
Stars
108
Forks
26
Language
Jupyter Notebook
License
—
Category
Last pushed
Aug 17, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/yufengm/SelfAttentive"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.