SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.08122 · 2021

Sequence-Level Training for Non-Autoregressive Neural Machine Translation

arXiv · PDF · Open in the Atlas

Code that ran

1 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 0 failures of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2106.08122.json · badge: /api/ran/2106.08122.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
ictnlp/Seq-NAT canonical (classifier label)
classifier basis: census
1 ran · 2 no recorded run
FunctionStatusWhere it lives
gumbel_noise Ran
ran on a synthesized input
ictnlp/Seq-NAT/fairseq/models/nat/iterative_nonautoregressive_transformer.py
pointer only (licence: MIT) · get_code("a2543dc608ad4f8a")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, ictnlp/Seq-NAT, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

ensemble_decoder Not yet run
unverified (harvested, no recorded run)
ictnlp/Seq-NAT/fairseq/models/nat/fairseq_nat_model.py
pointer only (licence: MIT) · get_code("8966a106dd26788e")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, ictnlp/Seq-NAT, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

ensemble_encoder Not yet run
unverified (harvested, no recorded run)
ictnlp/Seq-NAT/fairseq/models/nat/fairseq_nat_model.py
pointer only (licence: MIT) · get_code("eaa91eaae9eb59f0")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, ictnlp/Seq-NAT, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 3 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 3 later) and 0 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
gumbel_noise 3 other papers
3 later
2205.14333 (2022-05)
One Reference Is Not Enough: Diverse Distillation with Reference Selection for Non-Autoregressive Translation
2210.03953 (2022-10)
Non-Monotonic Latent Alignments for CTC-Based Non-Autoregressive Machine Translation
2210.11017 (2022-10)
Multi-Granularity Optimization for Non-Autoregressive Translation
ensemble_decoder 2 other papers
2 later
2205.14333 (2022-05)
One Reference Is Not Enough: Diverse Distillation with Reference Selection for Non-Autoregressive Translation
2210.03953 (2022-10)
Non-Monotonic Latent Alignments for CTC-Based Non-Autoregressive Machine Translation
ensemble_encoder 2 other papers
2 later
2205.14333 (2022-05)
One Reference Is Not Enough: Diverse Distillation with Reference Selection for Non-Autoregressive Translation
2210.03953 (2022-10)
Non-Monotonic Latent Alignments for CTC-Based Non-Autoregressive Machine Translation

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

In recent years, Neural Machine Translation (NMT) has achieved notable results in various translation tasks. However, the word-by-word generation manner determined by the autoregressive mechanism leads to high translation latency of the NMT and restricts its low-latency applications. Non-Autoregressive Neural Machine Translation (NAT) removes the autoregressive mechanism and achieves significant decoding speedup through generating target words independently and simultaneously. Nevertheless, NAT still takes the word-level cross-entropy loss as the training objective, which is not optimal because the output of NAT cannot be properly evaluated due to the multimodality problem. In this article, we propose using sequence-level training objectives to train NAT models, which evaluate the NAT outputs as a whole and correlates well with the real translation quality. Firstly, we propose training NAT models to optimize sequence-level evaluation metrics (e.g., BLEU) based on several novel reinforcement algorithms customized for NAT, which outperforms the conventional method by reducing the variance of gradient estimation. Secondly, we introduce a novel training objective for NAT models, which aims to minimize the Bag-of-Ngrams (BoN) difference between the model output and the reference sentence. The BoN training objective is differentiable and can be calculated efficiently without doing any approximations. Finally, we apply a three-stage training strategy to combine these two methods to train the NAT model. We validate our approach on four translation tasks (WMT14 En$\leftrightarrow$De, WMT16 En$\leftrightarrow$Ro), which shows that our approach largely outperforms NAT baselines and achieves remarkable performance on all translation tasks. The source code is available at https://github.com/ictnlp/Seq-NAT.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2106.08122")
get_code_for_paper("2106.08122")
have("2106.08122")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2106.08122.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2106.08122.svg)](https://syntology.ai/paper/2106.08122)

Connect an agent — have() is free.