Machine translation systems trained without parallel corpora are the coolest shit. *shaking head* Amazing.
-
-
-
Replying to @nerpulus
First you find word vector correspondences: http://nlp.csai.tsinghua.edu.cn/~ly/papers/acl2017_zm.pdf … & http://www.aclweb.org/anthology/W/W16/W16-1614.pdf … Once you have multilingual embeddings, you can use denoising and back-translation to make full translation models: https://arxiv.org/pdf/1710.11041.pdf … https://arxiv.org/pdf/1711.00043.pdf …
1 reply 0 retweets 0 likes
Replying to @preinfarction @nerpulus
They're not amazingly good at translating, but they are magical, and a small miracle is still worth marveling over.
8:08 PM - 26 Feb 2018
0 replies
0 retweets
0 likes
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.