Building Machine Translation Systems for the Next Thousand Languages — mentioned by svat

Wed, 04 Oct 2023 02:57:36 GMT

It's a great question. But note that Google Translate is also trained on "predict the missing token": https://blog.research.google/2022/05/24-new-languages-google... / https://arxiv.org/abs/2205.03983 (search the blog post around “Surprisingly, this simple procedure produces high quality zero-shot translations.”) This was in May 2022, as part of Google Translate adding support for several low-resource languages (including Sanskrit). I was already very surprised that simply training on predicting tokens does translation so well — then a few months later ChatGPT came out, trained (roughly) the…

Paper and discussion history. A mention is not an endorsement.

Building Machine Translation Systems for the Next Thousand Languages — mentioned by albertzeyer

Wed, 06 Jul 2022 22:13:19 GMT

Note that very recently Google has done something very similar: "Building Machine Translation Systems for the Next Thousand Languages": https://arxiv.org/abs/2205.03983 https://ai.googleblog.com/2022/05/24-new-languages-google-tr... The Facebook paper has some direct comparison to that work.

Paper and discussion history. A mention is not an endorsement.

Building Machine Translation Systems for the Next Thousand Languages · HackerPapers discussions

Building Machine Translation Systems for the Next Thousand Languages — mentioned by svat

Building Machine Translation Systems for the Next Thousand Languages — mentioned by albertzeyer