SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.10369 · ICLR · 2021

Deep Encoder, Shallow Decoder: Reevaluating Non-autoregressive Machine Translation

Jungo Kasai, James Cross, Nikolaos Pappas, Hao Peng, Noah ♡♢

arXiv · PDF · Open in the Atlas

Code that ran

3 of 5 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 2 have no contract verdict; 1 failure 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/2006.10369.json · badge: /api/ran/2006.10369.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
jungokasai/deep-shallow canonical (classifier label)
classifier basis not recorded on the link
1 ran · 0 no recorded run
snoop2head/Deep-Encoder-Shallow-Decoder community (classifier label)
classifier basis not recorded on the link
2 ran · 2 no recorded run
FunctionStatusWhere it lives
cleanse_broken Ran
ran on a synthesized input
snoop2head/Deep-Encoder-Shallow-Decoder/preprocess.py
code served (permissive licence) · get_code("a5f26521dfecfd30")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned DataFrame. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import pandas as pd
import numpy as np

# Create a sample DataFrame with some empty values and spaces
df_input = pd.DataFrame({
    'col1': ['a', 'b', '', 'd'],
    'col2': [1, 2, 3, 4],
    'col3': ['x', ' ', 'z', 'w'],
    'col4': [10, 20, 30, 40]
})

ARGS = {
    'df_input': df_input
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DataFrame — a DataFrame output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataFrame output the recorded ndim 2 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
custom_collate_fn Ran
ran on a synthesized input
snoop2head/Deep-Encoder-Shallow-Decoder/dataset.py
code served (permissive licence) · get_code("8d980fbded1762a7")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# The function expects a batch parameter which is an iterable of (src_sample, tgt_sample) tuples
# Each sample should be convertible to a tensor via torch.tensor()
# Based on the function body, src_batch and tgt_batch are lists that get converted to tensors
# and then transposed from (0,1), meaning the input tuples should contain sequences/arrays

# Create small sample data
# Using distinct sizes: 3 source sequence length, 4 target sequence length
batch = [
    ([1, 2, 3], [4, 5, 6, 7]),  # First pair: src length 3, tgt length 4
    ([8, 9, 10], [11, 12, 13, 14]),  # Second pair: src length 3, tgt length 4
]

ARGS = {
    "batch": batch
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
safe_readline Ran
ran; our contract draft was wrong, not the code
jungokasai/deep-shallow/fairseq/binarizer.py
pointer only (licence: MIT); the stored copy get_code serves, from agi-content-generation/EKD, is pointer only (licence: NOASSERTION) · get_code("82bdf940665aeeb4")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, jungokasai/deep-shallow, 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.

custom_collate_inference_fn Not yet run
unverified (harvested, no recorded run)
snoop2head/Deep-Encoder-Shallow-Decoder/dataset.py
code served (permissive licence) · get_code("7ef1cf63594e8444")
How it ran

no invocation recorded.

generate_square_subsequent_mask Not yet run
unverified (harvested, no recorded run)
snoop2head/Deep-Encoder-Shallow-Decoder/trainer.py
code served (permissive licence) · get_code("b123ed9c3b4a5518")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 2 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 2 later) and 3 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
safe_readline 66 other papers
10 dated earlier, 1 the same month, 55 later
1610.02424 (2016-10)
Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models
1802.06901 (2018-02)
Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinement
1904.01038 (2019-04)
FAIRSEQ: A Fast, Extensible Toolkit for Sequence Modeling
and 63 more not named here
generate_square_subsequent_mask 4 other papers
4 later
2211.07727 (2022-11)
Logical Tasks for Measuring Extrapolation and Rule Comprehension
aaai_25328 (2023 (year only))
Text-DIAE: A Self-Supervised Degradation Invariant Autoencoder for Text Recognition and Document Enhancement
2310.11984 (2023-10)
From Interpolation to Extrapolation: Complete Length Generalization for Arithmetic Transformers
and 1 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

Much recent effort has been invested in non-autoregressive neural machine translation, which appears to be an efficient alternative to state-of-the-art autoregressive machine translation on modern GPUs. In contrast to the latter, where generation is sequential, the former allows generation to be parallelized across target token positions. Some of the latest non-autoregressive models have achieved impressive translation quality-speed tradeoffs compared to autoregressive baselines. In this work, we reexamine this tradeoff and argue that autoregressive baselines can be substantially sped up without loss in accuracy. Specifically, we study autoregressive models with encoders and decoders of varied depths. Our extensive experiments show that given a sufficiently deep encoder, a single-layer autoregressive decoder can substantially outperform strong non-autoregressive models with comparable inference speed. We show that the speed disadvantage for autoregressive baselines compared to non-autoregressive methods has been overestimated in three aspects: suboptimal layer allocation, insufficient speed measurement, and lack of knowledge distillation. Our results establish a new protocol for future research toward fast, accurate machine translation. Our code is available at https://github.com/jungokasai/deep-shallow.

For agents

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

get_harvested_code_for_paper("2006.10369")
get_code_for_paper("2006.10369")
have("2006.10369")

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

curl https://syntology.ai/api/ran/2006.10369.json

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

[![Syntology run record](https://syntology.ai/api/ran/2006.10369.svg)](https://syntology.ai/paper/2006.10369)

Connect an agent — have() is free.