FranxYao/pivot_analysis
Implementation of INLG 19 paper: Rethinking Text Attribute Transfer: A Lexical Analysis
This project helps you understand which specific words drive the sentiment or style of text in large datasets like product reviews, social media posts, or news articles. It takes a collection of text labeled with different attributes (like 'positive' or 'negative') and identifies the key 'pivot' words that are most indicative of each attribute. The output includes lists of these pivot words, their precision and recall, and examples of how they appear in sentences, enabling analysts to quickly pinpoint influential vocabulary.
No commits in the last 6 months.
Use this if you need to quantitatively identify, measure, and visualize the impact of individual words on text attributes like sentiment or style within your datasets.
Not ideal if you are looking for a tool to perform actual text style transfer or generate new text content.
Stars
16
Forks
5
Language
Python
License
—
Category
Last pushed
Sep 30, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/FranxYao/pivot_analysis"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
PrithivirajDamodaran/Styleformer
A Neural Language Style Transfer framework to transfer natural language text smoothly between...
Nrgeup/controllable-text-attribute-transfer
Code for "Controllable Unsupervised Text Attribute Transfer via Editing Entangled Latent...
fuzhenxin/Style-Transfer-in-Text
Paper List for Style Transfer in Text
hayj/DeepStyle
DeepStyle provides pretrained models aiming to project text in a stylometric space. The base...
yd1996/awesome-text-style-transfer
A list of resources about Text Style Transfer