The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation · HackerPapers discussions

The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation — mentioned by umeshunni

Thu, 30 Jul 2026 04:12:15 GMT

and Google Translate: https://arxiv.org/abs/1804.09849

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

The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation — mentioned by albertzeyer

Tue, 04 Feb 2025 08:58:52 GMT

It's really a pity that they do this now. Some of their older papers had actually quite some valuable information, comments, discussions, thoughts, even commented out sections, figures, tables in it. It gave a much better view on how the paper was written over time, or how even the work processed over time. Sometimes you also see some alternative titles being discussed, which can be quite funny. E.g. from https://arxiv.org/abs/1804.09849: %\title{Sequence-to-Sequence Tricks and Hybrids\\for Improved Neural Machine Translation} % \title{Mixing and Matching Sequence-to-Sequence Modeling…

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

The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation — mentioned by albertzeyer

Tue, 02 Oct 2018 21:11:13 GMT

Transformer has gained lots of traction since it was introduced, and has become kind of a standard model for translation now, being better in many/some cases for machine translation. The transformer is different to the previous recurrent neural network (RNN) model (LSTM usually) (together with attention) in that it does not use RNNs/LSTMs at all, but just attention instead (that is why the paper was called "attention is all you need" (https://arxiv.org/abs/1706.03762 )). However, note that there was an update by Google recently, "The Best of Both Worlds: Combining Recent Advances in Neural…

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

The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation — mentioned by nmca

Sun, 24 Jun 2018 19:29:06 GMT

The latter of those two points is much more valid than the former. You're comment about generalisation difficulty is pretty accurate, but as for "sucks at variable length data", I think neural machine translation [0] and the fact that schemes including RNNs just won M4 [1] indicate that this is incorrect. Your point about remembering the past is true (it's hard), but people are actively working on it. Unitary neural nets, and the fast/slow weight paradigm are very different angles that seem promising. As for handling trees + graphs, this actually works very well. Thomas Kipf is pushing this…

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

The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation — HN submission

Wed, 02 May 2018 08:53:24 GMT

The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation

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