zwhe99/SelfTraining4UNMT
[ACL 2022] Bridging the Data Gap between Training and Inference for Unsupervised Neural Machine Translation
This project offers an improved method for Unsupervised Neural Machine Translation (UNMT), which translates text between languages without needing parallel sentences (text translated by humans). It takes monolingual text data in two languages and produces a machine translation model capable of translating between them. This is primarily useful for researchers and machine translation engineers working on advanced language processing systems.
No commits in the last 6 months.
Use this if you are a researcher or engineer looking to advance the state-of-the-art in unsupervised neural machine translation, particularly for English-French, English-German, or English-Romanian language pairs.
Not ideal if you need an out-of-the-box translation service for general business use, as this requires significant technical expertise to set up and run.
Stars
31
Forks
1
Language
Python
License
—
Category
Last pushed
Oct 06, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/zwhe99/SelfTraining4UNMT"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
princeton-nlp/SimCSE
[EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821
n-waves/multifit
The code to reproduce results from paper "MultiFiT: Efficient Multi-lingual Language Model...
yxuansu/SimCTG
[NeurIPS'22 Spotlight] A Contrastive Framework for Neural Text Generation
alibaba-edu/simple-effective-text-matching
Source code of the ACL2019 paper "Simple and Effective Text Matching with Richer Alignment Features".
Shark-NLP/OpenICL
OpenICL is an open-source framework to facilitate research, development, and prototyping of...