Papers › Fine-Tuning by Curriculum Learning for Non-Autoregressive Neural Machine Translation

Fine-Tuning by Curriculum Learning for Non-Autoregressive Neural Machine Translation

20 Nov 2019arXiv:1911.08717archive 2025-07-28

Junliang Guo, Xu Tan, Linli Xu, Tao Qin, Enhong Chen, Tie-Yan Liu

Non-autoregressive translation (NAT) models remove the dependence on previous target tokens and generate all target tokens in parallel, resulting in significant inference speedup but at the cost of inferior translation accuracy compared to autoregressive translation (AT) models. Considering that AT models have higher accuracy and are easier to train than NAT models, and both of them share the same model configurations, a natural idea to improve the accuracy of NAT models is to transfer a well-trained AT model to an NAT model through fine-tuning. However, since AT and NAT models differ greatly in training strategy, straightforward fine-tuning does not work well. In this work, we introduce curriculum learning into fine-tuning for NAT. Specifically, we design a curriculum in the fine-tuning process to progressively switch the training from autoregressive generation to non-autoregressive generation. Experiments on four benchmark translation datasets show that the proposed method achieves good improvement (more than 1 BLEU score) over previous NAT baselines in terms of translation accuracy, and greatly speed up (more than 10 times) the inference process over AT baselines.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 12 code samples harvested from 1 repository linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 12 samples from 1 repository, 11 ran (11 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

lemmonation/fcl-nat officialmentioned in papermentioned on GitHubtfMITSyntology: 12 samples, 11 ran (0 instrument-failed) · 1 unverified report
josephch405/curriculum-nmt mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Improving Neural Machine Translation Models with Monolingual Data (arXiv:1511.06709; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

12 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

11ran
1unverified

Licence: 0 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from lemmonation/fcl-nat. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

lemmonation/fcl-nat official repository 12 samples, 11 ran (0 instrument-failed) · 1 unverified
add_standard_attention_hparams tensor2tensor/layers/common_attention.py ran MIT (permissive) · 44e847faaba1328c · report fixture: signature hparams:HParams/0/? · returned HParams · level recorded 2026-09-25
attention_bias_without_self tensor2tensor/models/transformer_nat_cl_word.py ran MIT (permissive) · 1cca0cf169d3512e · report fixture: signature length:int/0/int · returned EagerTensor · level recorded 2026-09-25
copy_batches tensor2tensor/models/transformer_nat_cl_word.py ran MIT (permissive) · ff01c7e565eb434e · report fixture: signature x:EagerTensor/2/float, num_copies:int/0/int · returned EagerTensor · level recorded 2026-09-25
hard_sigmoid in 15 papers tensor2tensor/layers/common_layers.py ran MIT (permissive) · 62078081af34b8ee · report fixture: signature x:EagerTensor/2/float, saturation_limit:float/0/float · returned tuple · level recorded 2026-09-25
hard_tanh tensor2tensor/layers/common_layers.py ran MIT (permissive) · dfdf8307a155fa8b · report fixture: signature x:EagerTensor/2/float, saturation_limit:float/0/float · returned tuple · level recorded 2026-09-25
is_in_expr tensor2tensor/data_generators/algorithmic_math.py ran MIT (permissive) · 7e2bc85a4d4189a9 · report fixture: signature expr:ExprNode/0/?, find:ExprNode/0/? · returned bool · level recorded 2026-09-25
lower_endian_to_number tensor2tensor/data_generators/algorithmic.py ran fingerprinted MIT (permissive) · b1896a2536602d28 · report fixture: signature l:list/1/int, base:int/0/int · returned int · level recorded 2026-09-25
random_expr tensor2tensor/data_generators/algorithmic_math.py ran MIT (permissive) · 916cc023d1d1ddbd · report fixture: signature depth:int/0/int, vlist:list/1/str, ops:list/1/ExprOp · returned ExprNode · level recorded 2026-09-25
random_expr_with_required_var tensor2tensor/data_generators/algorithmic_math.py ran MIT (permissive) · 0a76872f8ddc4b1e · report fixture: signature depth:int/0/int, required_var:str/0/str, optional_list:list/1/str, ops:list/1/ExprOp · returned ExprNode · level recorded 2026-09-25
zipf_distribution tensor2tensor/data_generators/algorithmic.py ran MIT (permissive) · 68fe9a15fc61f6bd · report fixture: signature nbr_symbols:int/0/int, alpha:float/0/float · returned list · level recorded 2026-09-25
zipf_random_sample tensor2tensor/data_generators/algorithmic.py ran MIT (permissive) · d0d6f2cc06f67920 · report fixture: signature distr_map:ndarray/1/float, sample_len:int/0/int · returned list · level recorded 2026-09-25
saturating_sigmoid tensor2tensor/layers/common_layers.py unverified MIT (permissive) · c53fad116e23fd5d · report

Tasks

Machine TranslationTranslation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SPEED

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections