SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1808.08583 · 2018

Semi-Autoregressive Neural Machine Translation

arXiv · PDF · Open in the Atlas

Code that ran

1 of 4 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; 3 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/1808.08583.json · badge: /api/ran/1808.08583.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
chqiwang/sa-nmt canonical (classifier label)
classifier basis: census
1 ran · 3 no recorded run
FunctionStatusWhere it lives
expand_feed_dict Ran
ran on a synthesized input
chqiwang/sa-nmt/utils.py
code served (permissive licence) · get_code("d06bd91b2997aec4")
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 dict. 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
import numpy as np

torch.manual_seed(0)

# Create test data
# The function expects feed_dict where keys can be placeholders (or tuples of placeholders)
# and values are tensors that get split across tuple keys

# Create a simple placeholder class
class Placeholder:
    def __init__(self, name):
        self.name = name
    
    def __repr__(self):
        return f"Placeholder({self.name})"

# Create placeholders
p1 = Placeholder("p1")
p2 = Placeholder("p2")
p3 = Placeholder("p3")

# Create test tensors
# Batch size 6 to allow even splitting across 2 and 3 placeholders
tensor_6 = torch.randn(6, 4)  # batch_size=6, features=4
tensor_5 = torch.randn(5, 3)  # batch_size=5, features=3 (tests remainder logic)
tensor_single = torch.randn(2, 2)  # batch_size=2, features=2

# Construct feed_dict with mix of tuple and non-tuple keys
feed_dict = {
    p1: tensor_single,  # non-tuple key
    (p2, p3): tensor_6,  # tuple key with 2 placeholders - splits 6 into [3, 3]
    "string_key": tensor_5,  # another non-tuple key
}

ARGS = {
    "feed_dict": feed_dict
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 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
average_gradients Not yet run
unverified (harvested, no recorded run)
chqiwang/sa-nmt/utils.py
code served (permissive licence) · get_code("3ad1487952836d07")
How it ran

no invocation recorded.

decoder_self_attention_bias Not yet run
unverified (harvested, no recorded run)
chqiwang/sa-nmt/models/sat.py
code served (permissive licence) · get_code("36fd928848e6906c")
How it ran

no invocation recorded.

pad_begin Not yet run
unverified (harvested, no recorded run)
chqiwang/sa-nmt/models/sat.py
code served (permissive licence) · get_code("3b8288c2246709d7")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 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
average_gradients 1 other paper
1 dated earlier
1703.04887 (2017-03)
Improving Neural Machine Translation with Conditional Sequence Generative Adversarial Nets

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

Existing approaches to neural machine translation are typically autoregressive models. While these models attain state-of-the-art translation quality, they are suffering from low parallelizability and thus slow at decoding long sequences. In this paper, we propose a novel model for fast sequence generation --- the semi-autoregressive Transformer (SAT). The SAT keeps the autoregressive property in global but relieves in local and thus is able to produce multiple successive words in parallel at each time step. Experiments conducted on English-German and Chinese-English translation tasks show that the SAT achieves a good balance between translation quality and decoding speed. On WMT'14 English-German translation, the SAT achieves 5.58$\times$ speedup while maintains 88\% translation quality, significantly better than the previous non-autoregressive methods. When produces two words at each time step, the SAT is almost lossless (only 1\% degeneration in BLEU score).

For agents

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

get_harvested_code_for_paper("1808.08583")
get_code_for_paper("1808.08583")
have("1808.08583")

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

curl https://syntology.ai/api/ran/1808.08583.json

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

[![Syntology run record](https://syntology.ai/api/ran/1808.08583.svg)](https://syntology.ai/paper/1808.08583)

Connect an agent — have() is free.