ogkalu2/Human-parity-on-machine-translations
Bilingual (or Multilingual) Large Language models and In-context Learning- The key to human parity on machine translations
This project explores how well large language models (LLMs) can translate between languages, especially those with very different grammars like English and Chinese. It takes Chinese literary text as input and produces English translations, comparing the quality against other popular translation tools. This is for anyone interested in the state-of-the-art in machine translation, particularly for complex texts.
No commits in the last 6 months.
Use this if you need to understand the current capabilities and limitations of AI for translating nuanced literary content between vastly different languages.
Not ideal if you're looking for a simple, production-ready translation API for everyday use or general business documents.
Stars
32
Forks
1
Language
—
License
—
Category
Last pushed
Feb 15, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/ogkalu2/Human-parity-on-machine-translations"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
OpenNMT/OpenNMT-py
Open Source Neural Machine Translation and (Large) Language Models in PyTorch
argosopentech/argos-translate
Open-source offline translation library written in Python
niedev/RTranslator
Open source real-time translation app for Android that runs locally
vistec-AI/thai2transformers
Pretraining transformer based Thai language models
Freed-Wu/translate-shell
Translate text by google, bing, youdaozhiyun, haici, stardict, openai, large language model of...