krishnap25/mauve
Package to compute Mauve, a similarity score between neural text and human text. Install with `pip install mauve-text`.
This tool helps researchers and practitioners evaluate how similar machine-generated text is to human-written text. You provide samples of text created by an AI model and samples of human-authored text. It then calculates a 'MAUVE score,' which indicates the degree of similarity, helping you understand the quality and naturalness of the AI's output. This is useful for anyone developing or assessing AI text generation systems, like those in natural language processing research or content creation.
308 stars. No commits in the last 6 months.
Use this if you need an objective and quantifiable way to compare the distribution and quality of AI-generated text against human text, to understand if your model's output is realistic and diverse.
Not ideal if you only need a qualitative assessment or subjective human feedback for text quality, or if you are working with very small text samples (less than a few thousand generations).
Stars
308
Forks
28
Language
Python
License
—
Category
Last pushed
Jul 12, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/krishnap25/mauve"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
patil-suraj/question_generation
Neural question generation using transformers
vinhkhuc/MemN2N-babi-python
End-To-End Memory Networks for bAbI question-answering tasks
nelson-liu/paraphrase-id-tensorflow
Various models and code (Manhattan LSTM, Siamese LSTM + Matching Layer, BiMPM) for the...
YuriyGuts/kaggle-quora-question-pairs
My solution to Kaggle Quora Question Pairs competition (Top 2%, Private LB log loss 0.13497).
dtrizna/slp
Shell Language Processing (SLP). Pre-processing of sh/bash/zsh/.. commands for Machine Learning models.