SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.01479 · 2024

Align-to-Distill: Trainable Attention Alignment for Knowledge Distillation in Neural Machine Translation

arXiv · PDF · Open in the Atlas

Code that ran

1 of 2 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 0 have no contract verdict; 1 failure of our instrument; 1 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/2403.01479.json · badge: /api/ran/2403.01479.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
ncsoft/Align-to-Distill canonical (classifier label)
classifier basis not recorded on the link
1 ran · 1 no recorded run
FunctionStatusWhere it lives
find_version Ran
ran; our contract draft was wrong, not the code
ncsoft/Align-to-Distill/release_utils.py
pointer only (licence: NONE) · get_code("d4192f5e85770fdd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ncsoft/Align-to-Distill when it was checked. 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.

get_next_version Not yet run
unverified (harvested, no recorded run)
ncsoft/Align-to-Distill/release_utils.py
pointer only (licence: NONE) · get_code("44b6e8848744468f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ncsoft/Align-to-Distill when it was checked. 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 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 2 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
find_version 12 other papers
10 dated earlier, 2 later
1907.06616 (2019-07)
Facebook FAIR's WMT19 News Translation Task Submission
2022.emnlp-main.663 (2022 (year only))
Learning with Rejection for Abstractive Text Summarization
2210.02592 (2022-10)
CCC-wav2vec 2.0: Clustering aided Cross Contrastive Self-supervised learning of speech representations
and 9 more not named here
get_next_version 12 other papers
10 dated earlier, 2 later
1907.06616 (2019-07)
Facebook FAIR's WMT19 News Translation Task Submission
2022.emnlp-main.663 (2022 (year only))
Learning with Rejection for Abstractive Text Summarization
2210.02592 (2022-10)
CCC-wav2vec 2.0: Clustering aided Cross Contrastive Self-supervised learning of speech representations
and 9 more not named here

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

The advent of scalable deep models and large datasets has improved the performance of Neural Machine Translation. Knowledge Distillation (KD) enhances efficiency by transferring knowledge from a teacher model to a more compact student model. However, KD approaches to Transformer architecture often rely on heuristics, particularly when deciding which teacher layers to distill from. In this paper, we introduce the 'Align-to-Distill' (A2D) strategy, designed to address the feature mapping problem by adaptively aligning student attention heads with their teacher counterparts during training. The Attention Alignment Module in A2D performs a dense head-by-head comparison between student and teacher attention heads across layers, turning the combinatorial mapping heuristics into a learning problem. Our experiments show the efficacy of A2D, demonstrating gains of up to +3.61 and +0.63 BLEU points for WMT-2022 De->Dsb and WMT-2014 En->De, respectively, compared to Transformer baselines.

For agents

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

get_harvested_code_for_paper("2403.01479")
get_code_for_paper("2403.01479")
have("2403.01479")

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

curl https://syntology.ai/api/ran/2403.01479.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.01479.svg)](https://syntology.ai/paper/2403.01479)

Connect an agent — have() is free.