SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2004.12681 · ACL · 2020

Lexically Constrained Neural Machine Translation with Levenshtein Transformer

Shamil Chollampatt, Raymond Susanto, Liling Tan

arXiv · PDF · Open in the Atlas

Code that ran

2 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 0 have no contract verdict; 2 failures 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/2004.12681.json · badge: /api/ran/2004.12681.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
raymondhs/constrained-levt canonical (classifier label)
classifier basis: census
2 ran · 2 no recorded run
FunctionStatusWhere it lives
load_checkpoint Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
raymondhs/constrained-levt/fairseq/checkpoint_utils.py
pointer only (licence: MIT) · get_code("9d23e0c118a7efa7")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, raymondhs/constrained-levt, 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
raymondhs/constrained-levt/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, raymondhs/constrained-levt, 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.

load_checkpoint_to_cpu Not yet run
unverified (harvested, no recorded run)
raymondhs/constrained-levt/fairseq/checkpoint_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from xssstory/SeqCo, is pointer only (licence: MIT) · get_code("7b2e4fc726cfcf16")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, raymondhs/constrained-levt, 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.

save_checkpoint Not yet run
unverified (harvested, no recorded run)
raymondhs/constrained-levt/fairseq/checkpoint_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from xssstory/SeqCo, is pointer only (licence: MIT) · get_code("4f5f25fa5d5cab34")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, raymondhs/constrained-levt, 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 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, 4 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 4 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
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
load_checkpoint 1 other paper
1 later
2006.05744 (2020-06)
MC-BERT: Efficient Language Pre-Training via a Meta Controller
load_checkpoint_to_cpu 1 other paper
1 later
aaai_21409 (2022 (year only))
Sequence Level Contrastive Learning for Text Summarization
save_checkpoint 1 other paper
1 later
aaai_21409 (2022 (year only))
Sequence Level Contrastive Learning for Text Summarization

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

This paper proposes a simple and effective algorithm for incorporating lexical constraints in neural machine translation. Previous work either required re-training existing models with the lexical constraints or incorporating them during beam search decoding with significantly higher computational overheads. Leveraging the flexibility and speed of a recently proposed Levenshtein Transformer model (Gu et al., 2019), our method injects terminology constraints at inference time without any impact on decoding speed. Our method does not require any modification to the training procedure and can be easily applied at runtime with custom dictionaries. Experiments on English-German WMT datasets show that our approach improves an unconstrained baseline and previous approaches.

For agents

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

get_harvested_code_for_paper("2004.12681")
get_code_for_paper("2004.12681")
have("2004.12681")

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

curl https://syntology.ai/api/ran/2004.12681.json

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

[![Syntology run record](https://syntology.ai/api/ran/2004.12681.svg)](https://syntology.ai/paper/2004.12681)

Connect an agent — have() is free.