SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2010.11085 · EMNLP · 2020

NeuSpell: A Neural Spelling Correction Toolkit

Graham Neubig, Danish Pruthi, Sai Jayanthi

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, 1 violated it and 0 have no contract verdict; 1 failure of our instrument; 2 no recorded run), measured 2026-11-22; 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/2010.11085.json · badge: /api/ran/2010.11085.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
neuspell/neuspell marked official in Papers with Code
Papers with Code archive
2 ran · 2 no recorded run
FunctionStatusWhere it lives
get_module_or_attr Ran
ran; our contract draft was wrong, not the code
neuspell/neuspell/neuspell/seq_modeling/models.py
code served (permissive licence) · get_code("5cfe3525aa07ec01")
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 module. 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 importlib
import torch

# Test case 1: Load a module without function name
ARGS = {
    "module_name": "math",
    "func_name": None
}
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 module — a module output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a module 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
is_module_available Ran
ran, violated the contract we drafted
neuspell/neuspell/neuspell/seq_modeling/models.py
code served (permissive licence) · get_code("c392b89ed879cdbe")
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) and returned bool, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 importlib

def is_module_available(module_name: str):
    """
    checks if a module is available or not (eg. _is_module_available("sentence_transformers"))
    Args:
        module_name (str): name of the model to check
    Returns:
        bool, if or not the given module exists
    """
    try:
        importlib.import_module(module_name)
    except Exception as e:
        return False
    return True


ARGS = {
    "module_name": "os"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
ElmoSCLSTM Not yet run
unverified (harvested, no recorded run)
neuspell/neuspell/neuspell/seq_modeling/models.py
code served (permissive licence) · get_code("b27bdf379024ef87")
How it ran

no invocation recorded.

get_pretrained_elmo Not yet run
unverified (harvested, no recorded run)
neuspell/neuspell/neuspell/seq_modeling/models.py
code served (permissive licence) · get_code("07f181b5d863802d")
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, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 4 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.

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

We introduce NeuSpell, an open-source toolkit for spelling correction in English. Our toolkit comprises ten different models, and benchmarks them on naturally occurring misspellings from multiple sources. We find that many systems do not adequately leverage the context around the misspelt token. To remedy this, (i) we train neural models using spelling errors in context, synthetically constructed by reverse engineering isolated misspellings; and (ii) use contextual representations. By training on our synthetic examples, correction rates improve by 9% (absolute) compared to the case when models are trained on randomly sampled character perturbations. Using richer contextual representations boosts the correction rate by another 3%. Our toolkit enables practitioners to use our proposed and existing spelling correction systems, both via a unified command line, as well as a web interface. Among many potential applications, we demonstrate the utility of our spell-checkers in combating adversarial misspellings. The toolkit can be accessed at neuspell.github.io. 1

For agents

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

get_harvested_code_for_paper("2010.11085")
get_code_for_paper("2010.11085")
have("2010.11085")

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

curl https://syntology.ai/api/ran/2010.11085.json

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

[![Syntology run record](https://syntology.ai/api/ran/2010.11085.svg)](https://syntology.ai/paper/2010.11085)

Connect an agent — have() is free.