naist-nlp/mbrs
A library for minimum Bayes risk (MBR) decoding
This tool helps natural language processing (NLP) researchers and engineers improve the quality of generated text, such as machine translations. You provide a list of candidate sentences for a given input, and the tool selects the best one based on various evaluation metrics and decoding strategies. The result is a single, higher-quality output sentence.
Use this if you need to select the most accurate or appropriate sentence from a set of generated text candidates for tasks like machine translation or text summarization.
Not ideal if you are looking for a tool to generate text from scratch rather than select from existing candidates.
Stars
52
Forks
7
Language
Python
License
MIT
Category
Last pushed
Nov 02, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/naist-nlp/mbrs"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
yaserkl/RLSeq2Seq
Deep Reinforcement Learning For Sequence to Sequence Models
kefirski/pytorch_RVAE
Recurrent Variational Autoencoder that generates sequential data implemented with pytorch
ctr4si/A-Hierarchical-Latent-Structure-for-Variational-Conversation-Modeling
PyTorch Implementation of "A Hierarchical Latent Structure for Variational Conversation...
georgian-io/Multimodal-Toolkit
Multimodal model for text and tabular data with HuggingFace transformers as building block for text data
nurpeiis/LeakGAN-PyTorch
A simple implementation of LeakGAN in PyTorch