SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2004.14524 · EMNLP · 2020

Simulated Multiple Reference Training Improves Low-Resource Machine Translation

Philipp Koehn, Matt Post, Huda Khayrallah, Brian Thompson

arXiv · PDF · Open in the Atlas

Code that ran

2 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, 1 violated it and 0 have no contract verdict; 1 failure of our instrument; 3 no recorded run), measured 2026-11-21; 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/2004.14524.json · badge: /api/ran/2004.14524.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
thompsonb/fairseq-smrt canonical (classifier label)
classifier basis: census
2 ran · 3 no recorded run
FunctionStatusWhere it lives
is_master Ran
ran, violated the contract we drafted
thompsonb/fairseq-smrt/fairseq/distributed_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from agi-content-generation/EKD, is pointer only (licence: NOASSERTION) · get_code("90b79fe15491de83")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, thompsonb/fairseq-smrt, 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.

safe_readline Ran
ran; our contract draft was wrong, not the code
thompsonb/fairseq-smrt/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, thompsonb/fairseq-smrt, 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.

all_reduce Not yet run
unverified (harvested, no recorded run)
thompsonb/fairseq-smrt/fairseq/distributed_utils.py
pointer only (licence: MIT) · get_code("59755e76d7c3f48b")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, thompsonb/fairseq-smrt, 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.

distributed_init Not yet run
unverified (harvested, no recorded run)
thompsonb/fairseq-smrt/fairseq/distributed_utils.py
pointer only (licence: MIT) · get_code("9d353f13a2262a52")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, thompsonb/fairseq-smrt, 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.

smrt_cross_entropy_loss Not yet run
unverified (harvested, no recorded run)
thompsonb/fairseq-smrt/fairseq/criterions/smrt_cross_entropy.py
pointer only (licence: MIT) · get_code("173463e3694ae78d")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, thompsonb/fairseq-smrt, 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 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, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 1 the same month, 3 later) and 2 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
6 dated earlier, 1 the same month, 59 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
is_master 18 other papers
2 dated earlier, 16 later
1610.02424 (2016-10)
Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models
1902.01388 (2019-02)
Re-examination of the Role of Latent Variables in Sequence Modeling
2005.02354 (2020-05)
It's Easier to Translate out of English than into it: Measuring Neural Translation Difficulty by Cross-Mutual Information
and 15 more not named here
all_reduce 4 other papers
1 dated earlier, 3 later
1902.01388 (2019-02)
Re-examination of the Role of Latent Variables in Sequence Modeling
2005.02354 (2020-05)
It's Easier to Translate out of English than into it: Measuring Neural Translation Difficulty by Cross-Mutual Information
2007.07691 (2020-07)
A Multilingual Parallel Corpora Collection Effort for Indian Languages
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 2026-11-21.

Repositories linked to this paper

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

Abstract

Many valid translations exist for a given sentence, yet machine translation (MT) is trained with a single reference translation, exacerbating data sparsity in low-resource settings. We introduce Simulated Multiple Reference Training (SMRT), a novel MT training method that approximates the full space of possible translations by sampling a paraphrase of the reference sentence from a paraphraser and training the MT model to predict the paraphraser's distribution over possible tokens. We demonstrate the effectiveness of SMRT in low-resource settings when translating to English, with improvements of 1.2 to 7.0 BLEU. We also find SMRT is complementary to back-translation.

For agents

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

get_harvested_code_for_paper("2004.14524")
get_code_for_paper("2004.14524")
have("2004.14524")

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

curl https://syntology.ai/api/ran/2004.14524.json

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

[![Syntology run record](https://syntology.ai/api/ran/2004.14524.svg)](https://syntology.ai/paper/2004.14524)

Connect an agent — have() is free.