Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation · HackerPapers discussions

Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation — mentioned by jacobolus

Mon, 28 Dec 2020 01:23:48 GMT

They use some kind of neural net thing for other languages. e.g. here is a paper https://arxiv.org/abs/1609.08144

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

Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation — mentioned by tommit

Tue, 18 Feb 2020 11:06:23 GMT

You definitely have good points, but since the post I responded to gave Alexa as an initial example, I kind of took that as baseline. I can't really argue with anecdotes, but I can ensure you that a whole lot has changed in Machine Translation in the past 7 years, starting with Google introducing Neural Machine Translation[1] to replace their statistical model, which would often behave in the way you described. That's why I specifically included idioms, which hadn't really been possible until then. It's not yet perfect, but it's crazy good at what it does and only getting better. I know AI…

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

Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation — mentioned by anewhnaccount2

Thu, 15 Mar 2018 08:47:24 GMT

Compare this to one of Google's blog post promoting their MT research: https://research.googleblog.com/2016/09/a-neural-network-for... It is: 1) More accurate, compared to hyperbole like e.g. "Bridging the Gap between Human and Machine Translation" we have right there in the title the domain: news. 2) A more impressive result. This result is on an independently set up evaluation framework, compared to Google's which used their own framework. Compare further the papers: https://arxiv.org/pdf/1609.08144.pdf https://www.microsoft.com/en-us/research/uploads/prod/2018/0... These researcher appear…

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

Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation — mentioned by Macuyiko

Tue, 07 Mar 2017 20:51:08 GMT

Well, yeah: https://arxiv.org/abs/1609.08144

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

Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation — mentioned by circuithunter

Tue, 07 Feb 2017 15:49:59 GMT

Machine translation is a big one. See the recent NY Times feature [1] and the arxiv paper [2]. Automated image captioning is another (used extensively by Facebook). [1] https://www.nytimes.com/2016/12/14/magazine/the-great-ai-awa... [2] https://arxiv.org/abs/1609.08144

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

Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation — mentioned by srush

Thu, 12 Jan 2017 18:31:58 GMT

The code implements a pretty close model to what Google Translate has published (https://arxiv.org/abs/1609.08144). However the two systems are likely trained on very different datasets.

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

Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation — mentioned by ma2rten

Mon, 09 Jan 2017 18:18:01 GMT

Google Translate Paper mentions TPUs as well: https://arxiv.org/abs/1609.08144

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

Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation — mentioned by ma2rten

Mon, 02 Jan 2017 20:28:32 GMT

No offense, but this person has no idea what they are talking about. Google published a paper that explains exactly what they are doing and provides metrics as well [1,2]. It's true that neural networks can not be easily applied to natural languages, but there are less obvious ways of applying them (namely Embeddings, LSTMs, Attention) and provided you have enough data and computational resources they give so much better results than any other method that it doesn't even help anymore to combine them. [1] https://arxiv.org/abs/1609.08144 [2] https://arxiv.org/abs/1611.04558 EDIT: I also don't…

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

Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation — mentioned by _murphys_law_

Wed, 16 Nov 2016 19:06:17 GMT

Original blog post and report (September) https://research.googleblog.com/2016/09/a-neural-network-for... https://arxiv.org/abs/1609.08144

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

Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation — mentioned by dyoo1979

Wed, 16 Nov 2016 16:52:56 GMT

https://arxiv.org/abs/1609.08144, as well as the References section at the bottom of: https://research.googleblog.com/2016/09/a-neural-network-for...

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

Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation — mentioned by dennybritz

Sun, 02 Oct 2016 18:40:56 GMT

A lot of recent research uses RL to "fine-tune" NLP models. A practical example would be Google's recently announced Machine Translation System (https://arxiv.org/abs/1609.08144). It uses RL to directly optimize BLEU scores on translated sentences. You'll find similar applications in state-of-the art models for chatbots for example. Though I agree, "widely used" may be somewhat of an overstatement. But it's becoming more common. On a side note, I actually think RL makes a lot of sense for many NLP problems and it would be super interesting to build a pure RL approach to language modeling or…

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

Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation — mentioned by mastazi

Thu, 29 Sep 2016 00:09:37 GMT

ArXiv paper: https://arxiv.org/abs/1609.08144 (Not yet on Arxiv Sanity Preserver, but should be added soon I guess)

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

Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation — mentioned by aub3bhat

Wed, 28 Sep 2016 22:14:34 GMT

Honestly this comment reads like an emotional outburst, by someone who has zero clue about the domain. Its very well known fact in AI/ML community, that Apple has almost little or no talent nor do they have any major efforts at organizational level (E.g. FAIR at FB, MSR, Brain & Deep Mind at Google). >> But in Machine Translation, Apple is ahead. LOL where did you get this from? I am pretty sure that Google NTM which was put in production yesterday is the state of the art. Also there are metrics e.g. in the report released yesterday you can find BLEU scores on WMT 2014 tasks, and the clear…

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

Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation — HN submission

Tue, 27 Sep 2016 13:21:24 GMT

Google’s Neural Machine Translation System

236 points; 97 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation — HN submission

Tue, 27 Sep 2016 04:22:42 GMT

Google's Neural Machine Translation: Bridging the Gap Between Humans and Machines

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.