On two machine translation tasks, Transformer models are reported to give better quality, parallelise more easily and train in significantly less time.

The paper

The paper's details are OpenAlex's; the citation count is OpenAlex's, 9 Oct 2026. The line on the paper is machine-written, as noted under Why it matters.

Why it matters

Written by Claude (claude-sonnet-5-5) on 17 Oct 2026 from the paper's abstract (as arXiv publishes it) and its OpenAlex record. Machine-written context to help a reader: it is not evidence, it moves no number, and it may be wrong. The quoted sentence is the claim; where it stands is computed from the record. If it misreads the paper, tell the stewards.

The story so far

1. 1

   What the authors did

   The authors designed a new network architecture without recurrence or convolutions and tested it on two machine translation tasks, WMT 2014 English-to-German and English-to-French. They also applied it to English constituency parsing.

   Machine-written from the paper's abstract, as noted under Why it matters.

2. 2

   What they found

   • The model reaches 28.4 BLEU on WMT 2014 English-to-German, over 2 BLEU above the previous best results, including ensembles.
   • On WMT 2014 English-to-French it sets a single-model state-of-the-art BLEU of 41.8 after 3.5 days of training on eight GPUs, a small fraction of the cost of the best earlier models.
   • The Transformer is also reported to generalise to English constituency parsing, with both large and limited training data.

   Machine-written from the paper's abstract, as noted under Why it matters.

3. 3

   What has been checked on Ecdysis

   Exuvia registered the claim on 17 October 2026, with a test written from the paper. No check has been filed yet.

What would check it

How far it has been checked

1. 1
   The object itself, checked againverification · not yet

   Not yet: re-run the paper's analysis on its own data, where the authors have published it.

2. 2
   New instances of the constructionreproduction · not yet

   Not yet: the same construction run afresh.

3. 3
   The designrobustness tests and arguments · not yet

   Nothing yet: change the method or the data and see whether it holds (a robustness test), or argue that the method does not test what the claim says.

How sure is the record?

Share this finding

Ready-made posts, written from the record. You post them yourself, from your own account; nothing is ever posted for anyone.

Click a post's text to select all of it. Both posts give the claim's standing on the record, and the longer one says what the checks show and what they do not; the wording changes when the record does. The longer post quotes the paper first, then gives the machine-written headline, marked as such; edit it as you like. To cite the claim, see Cite this claim.

What would prove it wrong

Refuted if an independent replication shows Transformer models to achieve lower BLEU scores, require more training time, or exhibit less parallelizable computation than the best recurrent or convolutional models on the same WMT 2014 English‑to‑German and English‑to‑French translation tasks.

The test as Exuvia registered it on 17 Oct 2026, written from the paper's words.

The wider literature

Other claims from the same paper

• uncheckedThe Transformer model scored 28.4 BLEU on WMT 2014 English-to-German translation, over 2 BLEU above earlier best results, including ensembles.“Our model achieves 28.4 BLEU on the WMT 2014 English-to-German translation task, improving over the existing best results, including ensembles by over 2 BLEU.”
• uncheckedOn WMT 2014 English-to-French translation, the Transformer reports a single-model BLEU of 41.8 after 3.5 days on eight GPUs, at a fraction of rivals' training cost.“On the WMT 2014 English-to-French translation task, our model establishes a new single-model state-of-the-art BLEU score of 41.8 after training for 3.5 days on eight GPUs, a small fraction of the tra…”
• uncheckedThe paper reports that the Transformer, a model built only on attention, also worked well on English constituency parsing, with large and with limited training data.“We show that the Transformer generalizes well to other tasks by applying it successfully to English constituency parsing both with large and limited training data.”

Headlines are machine-written from the paper's abstract, or from the quote and the paper's title where no abstract is open; each claim's own words are quoted beneath its headline.