Papers › Spelling Error Correction with Soft-Masked BERT

Spelling Error Correction with Soft-Masked BERT

15 May 2020ACL 2020 6arXiv:2005.07421archive 2025-07-28

Shaohua Zhang, Haoran Huang, Jicong Liu, Hang Li

Spelling error correction is an important yet challenging task because a satisfactory solution of it essentially needs human-level language understanding ability. Without loss of generality we consider Chinese spelling error correction (CSC) in this paper. A state-of-the-art method for the task selects a character from a list of candidates for correction (including non-correction) at each position of the sentence on the basis of BERT, the language representation model. The accuracy of the method can be sub-optimal, however, because BERT does not have sufficient capability to detect whether there is an error at each position, apparently due to the way of pre-training it using mask language modeling. In this work, we propose a novel neural architecture to address the aforementioned issue, which consists of a network for error detection and a network for error correction based on BERT, with the former being connected to the latter with what we call soft-masking technique. Our method of using `Soft-Masked BERT' is general, and it may be employed in other language detection-correction problems. Experimental results on two datasets demonstrate that the performance of our proposed method is significantly better than the baselines including the one solely based on BERT.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 17 code samples harvested from 5 repositories linked to this paper: 14 ran (of which 2 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 17 samples from 5 repositories, 14 ran (13 with no instrument failure; 1 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

gitabtion/BertBasedCorrectionModels mentioned on GitHubpytorchApache-2.0Syntology: 7 samples, 6 ran (1 instrument-failed) · 1 unverified report
hiyoung123/SoftMaskedBert mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
lemon234071/TransformerBaselines mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
nocoolsandwich/pinyin_gen_error_sentence mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
mszpc/SoftMaskedBert mindsporeApache-2.0Syntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

17 samples harvested: 14 ran (of which 2 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · our draft was wrong
13ran
3unverified

Licence: 3 of the 17 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 5 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

gitabtion/BertBasedCorrectionModels community (archive-listed) 7 samples, 6 ran (1 instrument-failed) · 1 unverified
compute_sentence_level_prf bbcm/utils/evaluations.py ran Apache-2.0 (permissive) · b088e76916ad21f3 · report fixture: signature results:list/1/tuple, logger:SimpleLogger/0/? · returned tuple · level recorded 2026-09-24
dump_json bbcm/utils/file_io.py ran Apache-2.0 (permissive) · 712509715b4485d4 · report fixture: signature obj:dict/0/?, fp:str/0/str · returned bool · level recorded 2026-09-24
get_cache_dir in 14 papers bbcm/utils/file_io.py ran Apache-2.0 (permissive) · 9f0e70bc9b57f335 · report fixture: signature cache_dir:NoneType/0/? · returned str · level recorded 2026-09-24
load_json in 344 papers bbcm/utils/file_io.py ran fingerprinted Apache-2.0 (permissive) · fa2946b9355af8b5 · report fixture: signature fp:str/0/str · returned dict · level recorded 2026-09-24
make_optimizer in 32 papers bbcm/solver/build.py ran · our draft was wrong Apache-2.0 (permissive) · 3c707eafb83ce730 · report fixture: signature cfg:Config/0/?, model:callable/0/? · returned SGD · level recorded 2026-09-22
report_prf bbcm/utils/evaluations.py ran Apache-2.0 (permissive) · 704deca2af268bca · report fixture: signature tp:int/0/int, fp:int/0/int, fn:int/0/int, phase:str/0/str, logger:MinimalLogger/0/?, return_dict:bool/0/bool · returned dict · level recorded 2026-09-24
compute_corrector_prf bbcm/utils/evaluations.py unverified Apache-2.0 (permissive) · 98cd0539309793ca · report
hiyoung123/SoftMaskedBert community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
SoftMaskedBert model/soft_masked_bert.py ran no licence file found · pointer only · 3f71761e83e0177e · report fixture: returned SoftMaskedBert · level recorded 2026-09-22
lemon234071/TransformerBaselines community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
BiGRU agents/bert/soft_masked_bert/soft_masked_bert.py ran fingerprinted Apache-2.0 (permissive) · 3e404afd004bb929 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-24
SoftMaskedBert agents/bert/soft_masked_bert/soft_masked_bert.py unverified Apache-2.0 (permissive) · 0d5cdc01abffb5cb · report
nocoolsandwich/pinyin_gen_error_sentence community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
BiGRU model/soft_masked_bert.py ran fingerprinted no licence file found · pointer only · a728cf7fd8651ddf · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-24
SoftMaskedBert model/soft_masked_bert.py ran no licence file found · pointer only · b722732fc955e68c · report fixture: returned SoftMaskedBert · level recorded 2026-09-22
mszpc/SoftMaskedBert community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
compute_correction_prf softmaskedbert/src/utils.py ran Apache-2.0 (permissive) · c06aca58c0b60862 · report fixture: signature results2:list/1/list, all_predict_true_index:list/1/list, all_gold_index:list/1/list · returned float · level recorded 2026-09-24
compute_corrector_prf softmaskedbert/src/utils.py ran Apache-2.0 (permissive) · 8b028660c9e94b5c · report fixture: signature results:list/1/tuple · returned tuple · level recorded 2026-09-24
compute_detection_prf softmaskedbert/src/utils.py ran Apache-2.0 (permissive) · ac8790d05ecb703c · report fixture: signature results1:list/1/tuple · returned tuple · level recorded 2026-09-24
dump_json softmaskedbert/preprocess_dataset.py ran Apache-2.0 (permissive) · 40e10fdbe38a163f · report fixture: signature obj:dict/0/?, fp:str/0/str · returned bool · level recorded 2026-09-24
proc_test_set softmaskedbert/preprocess_dataset.py unverified Apache-2.0 (permissive) · c3ba3217b15fd141 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

3 assemblies on this paper: 3 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

3 sibling assemblies for Soft-Masked BERT (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Soft-Masked BERT (graph method: Soft-Masked BERT). 2 bricks; individually on a fixture: 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. SoftMaskedBert entry · level 1 · ran · b722732fc955e68c
  2. BiGRU helper · level 1 · ran · a728cf7fd8651ddf

harvested Assembly for Soft-Masked BERT (graph method: Soft-Masked BERT). 2 bricks; individually on a fixture: 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. SoftMaskedBert entry · level 1 · ran · 3f71761e83e0177e
  2. BiGRU model · level 1 · ran · a728cf7fd8651ddf

harvested Assembly for Soft-Masked BERT (graph method: Soft-Masked BERT). 2 bricks; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. SoftMaskedBert entry · level 0 · unverified · 0d5cdc01abffb5cb
  2. BiGRU model · level 1 · ran · 3e404afd004bb929

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2005.07421") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Chinese Spelling Error CorrectionLanguage ModelingLanguage ModellingSentence

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdamAttentionAttention DropoutBERTDense ConnectionsDropoutLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionResidual ConnectionSoftmaxWeight DecayWordPiece

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections