Papers › Revisiting Pre-Trained Models for Chinese Natural Language Processing

Revisiting Pre-Trained Models for Chinese Natural Language Processing

29 Apr 2020Findings of the Association for Computational Linguistics 2020arXiv:2004.13922archive 2025-07-28

Yiming Cui, Wanxiang Che, Ting Liu, Bing Qin, Shijin Wang, Guoping Hu

Bidirectional Encoder Representations from Transformers (BERT) has shown marvelous improvements across various NLP tasks, and consecutive variants have been proposed to further improve the performance of the pre-trained language models. In this paper, we target on revisiting Chinese pre-trained language models to examine their effectiveness in a non-English language and release the Chinese pre-trained language model series to the community. We also propose a simple but effective model called MacBERT, which improves upon RoBERTa in several ways, especially the masking strategy that adopts MLM as correction (Mac). We carried out extensive experiments on eight Chinese NLP tasks to revisit the existing pre-trained language models as well as the proposed MacBERT. Experimental results show that MacBERT could achieve state-of-the-art performances on many NLP tasks, and we also ablate details with several findings that may help future research. Resources available: https://github.com/ymcui/MacBERT

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

The archive's official repository (ymcui/MacBERT) was not harvested; the 35 samples below come from 3 community repositories.

Syntology 35 code samples harvested from 3 repositories linked to this paper: 21 ran (of which 1 constructed an object rather than computing a result; 15 with no instrument failure: 3 honoured, 0 violated, 12 with no contract checked; 6 where Syntology's instrument failed) · 14 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 35 samples from 3 repositories, 21 ran (15 with no instrument failure; 6 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 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

ymcui/MacBERT officialmentioned in papermentioned on GitHubtfApache-2.0Syntology: not harvested report
shibing624/pycorrector mentioned on GitHubtfSyntology: 8 samples, 4 ran (1 instrument-failed) · 4 unverified report
ymcui/Chinese-BERT-wwm mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
ymcui/Chinese-ELECTRA mentioned on GitHubtfApache-2.0Syntology: 7 samples, 5 ran (0 instrument-failed) · 2 unverified report
ymcui/Chinese-PreTrained-XLNet mentioned on GitHubtfApache-2.0Syntology: 20 samples, 12 ran (5 instrument-failed) · 8 unverified report
ymcui/Chinese-XLNet mentioned on GitHubtfApache-2.0Syntology: not harvested 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

35 samples harvested: 21 ran (of which 1 constructed an object rather than computing a result; 15 with no instrument failure: 3 honoured, 0 violated, 12 with no contract checked; 6 where Syntology's instrument failed) · 14 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · honoured contract
5ran · our draft was wrong
1ran; the contract check could not run
12ran
14unverified

Licence: 4 of the 35 samples are pointer only, meaning Syntology does not serve that copy's text. For 4 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

shibing624/pycorrector community (archive-listed) 8 samples, 4 ran (1 instrument-failed) · 4 unverified
FocalLoss in 9 papers pycorrector/macbert/macbert4csc.py ran Apache-2.0 (permissive) · 49538ded4b211b0d · report fixture: returned FocalLoss · level recorded 2026-09-22
compute_corrector_prf pycorrector/macbert/macbert4csc.py ran · honoured contract Apache-2.0 (permissive) · bc8cd524a10a5326 · report fixture: signature results:list/1/tuple, logger:Logger/0/? · returned tuple · level recorded 2026-09-22
compute_sentence_level_prf pycorrector/macbert/macbert4csc.py ran · honoured contract Apache-2.0 (permissive) · 731b5640fb2a2a52 · report fixture: signature results:list/1/tuple, logger:Logger/0/? · returned tuple · level recorded 2026-09-22
make_optimizer in 32 papers pycorrector/macbert/macbert4csc.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
BaseTrainingEngine pycorrector/macbert/macbert4csc.py unverified Apache-2.0 (permissive) · cfac541eefda5168 · report
CscTrainingModel pycorrector/macbert/macbert4csc.py unverified Apache-2.0 (permissive) · af8425a9c3022046 · report
MacBert4Csc pycorrector/macbert/macbert4csc.py unverified Apache-2.0 (permissive) · f5ffeb1faccdd442 · report
build_lr_scheduler in 13 papers pycorrector/macbert/macbert4csc.py unverified Apache-2.0 (permissive) · 699577a393a1a36e · report
ymcui/Chinese-ELECTRA community (archive-listed) 7 samples, 5 ran (0 instrument-failed) · 2 unverified
create_int_feature in 14 papers build_pretraining_dataset.py ran Apache-2.0 (permissive) · b03d45af664a39e3 · report fixture: signature values:list/1/int · returned Feature · level recorded 2026-09-26
find_lcs cmrc2018_drcd_evaluate.py ran fingerprinted Apache-2.0 (permissive) · b71224516be1ddfa · report fixture: signature s1:str/0/str, s2:str/0/str · returned tuple · level recorded 2026-09-24
gelu in 308 papers
census: 43 implementations from 74 papers, 6 distinct outputs on one shared input
model/modeling.py ran Apache-2.0 (permissive) · 9c6c6f379ebe0c8e · report fixture: signature input_tensor:SymbolicTensor/2/float · returned SymbolicTensor · level recorded 2026-09-24
get_activation in 218 papers model/modeling.py ran Apache-2.0 (permissive) · b2dfae5f1625da67 · report fixture: signature activation_string:str/0/str · returned function · level recorded 2026-09-24
get_assignment_map_from_checkpoint in 32 papers model/modeling.py ran Apache-2.0 (permissive) · cb34c9c201e23b66 · report fixture: signature tvars:list/1/ResourceVariable, init_checkpoint:str/0/str, prefix:str/0/str · returned tuple · level recorded 2026-09-24
mixed_segmentation in 5 papers cmrc2018_drcd_evaluate.py unverified Apache-2.0 (permissive) · 2ac9d5179c0b5c85 · report
remove_punctuation in 14 papers cmrc2018_drcd_evaluate.py unverified Apache-2.0 (permissive) · 5a2e0cd001c9f26b · report
ymcui/Chinese-PreTrained-XLNet community (archive-listed) 20 samples, 12 ran (5 instrument-failed) · 8 unverified
assign_to_gpu src/gpu_utils.py ran Apache-2.0 (permissive) · 6b2a8f1c93d0b071 · report fixture: signature gpu:int/0/int, ps_dev:str/0/str · returned function · level recorded 2026-09-25
batchify in 71 papers
census: 6 implementations from 6 papers, 3 distinct outputs across 3 buckets, one shared input per bucket
src/data_utils.py ran Apache-2.0 (permissive) · 8fa4efe75d3345a4 · report fixture: signature data:ndarray/1/int, bsz_per_host:int/0/int, sent_ids:ndarray/1/int · returned tuple · level recorded 2026-09-24
create_run_config src/xlnet.py ran Apache-2.0 (permissive) · b9e225229ba459c3 · report fixture: signature is_training:bool/0/bool, is_finetune:bool/0/bool, FLAGS:FLAGSConfig/0/? · returned RunConfig · level recorded 2026-09-24
encode_pieces src/prepro_utils.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · 0de7059b7a331eb0 · report fixture: signature sp_model:MockSentencePieceModel/0/?, text:str/0/str, return_unicode:bool/0/bool, sample:bool/0/bool · returned list · level recorded 2026-09-25
format_filename src/data_utils.py ran Apache-2.0 (permissive) · b86bea980cfb5cbf · report fixture: signature prefix:str/0/str, bsz_per_host:int/0/int, seq_len:int/0/int, bi_data:bool/0/bool, suffix:str/0/str, mask_alpha:int/0/int, mask_beta:int/0/int, reuse_len:int/0/int, uncased:bool/0/bool, fixed_num_predict:int/0/int · returned str · level recorded 2026-09-24
gelu in 308 papers
census: 43 implementations from 74 papers, 6 distinct outputs on one shared input
src/modeling.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · d08f324f950148de · report fixture: signature x:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-22
get_tokens in 40 papers src/squad_utils.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · aa6bc32d9c17a2f1 · report fixture: signature s:str/0/str · returned list · level recorded 2026-09-22
make_qid_to_has_ans in 14 papers src/squad_utils.py ran · our draft was wrong Apache-2.0 (permissive) · e91c44f5680827e2 · report fixture: signature dataset:list/1/dict · returned dict · level recorded 2026-09-22
normalize_answer in 304 papers src/squad_utils.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 6a96435eba311b08 · report fixture: signature s:str/0/str · returned str · level recorded 2026-09-22
positional_embedding src/modeling.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · 9bf0f6e6298f3fbe · report fixture: signature pos_seq:EagerTensor/1/float, inv_freq:EagerTensor/1/float, bsz:int/0/int · returned EagerTensor · level recorded 2026-09-22
preprocess_text in 26 papers src/prepro_utils.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · b19697c998adb1ea · report fixture: signature inputs:str/0/str, lower:bool/0/bool, remove_space:bool/0/bool, keep_accents:bool/0/bool · returned str · level recorded 2026-09-25
printable_text in 36 papers src/prepro_utils.py ran · our draft was wrong Apache-2.0 (permissive) · 0e5615f8994003cf · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-26
average_grads_and_vars src/gpu_utils.py unverified Apache-2.0 (permissive) · 0e3f1e158da4c3b8 · report
configure_tpu src/model_utils.py unverified Apache-2.0 (permissive) · 09d1e0e9c15a4503 · report
construct_scalar_host_call src/function_builder.py unverified Apache-2.0 (permissive) · c09b2ad22d30dc58 · report
create_tfrecords src/data_utils.py unverified Apache-2.0 (permissive) · 8e58d7fe314fa0a1 · report
embedding_lookup in 9 papers src/modeling.py unverified Apache-2.0 (permissive) · 5abf0267f0fc7514 · report
file_based_input_fn_builder in 16 papers src/run_classifier.py unverified Apache-2.0 (permissive) · aab5156ced02aa8a · report
init_from_checkpoint src/model_utils.py unverified Apache-2.0 (permissive) · 7b1d9794b90b3ae2 · report
load_from_checkpoint in 9 papers src/gpu_utils.py unverified Apache-2.0 (permissive) · 3d6b054785523852 · 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.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for MacBERT (graph method: MacBERT). 8 bricks; individually on a fixture: 4 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

  1. MacBert4Csc entry · level 0 · unverified · f5ffeb1faccdd442
  2. CscTrainingModel helper · level 0 · unverified · af8425a9c3022046
  3. FocalLoss loss · level 1 · ran · 49538ded4b211b0d
  4. BaseTrainingEngine helper · level 0 · unverified · cfac541eefda5168
  5. compute_corrector_prf helper · level 1 · ran · honoured contract · bc8cd524a10a5326
  6. compute_sentence_level_prf helper · level 1 · ran · honoured contract · 731b5640fb2a2a52
  7. build_lr_scheduler helper · level 0 · unverified · 699577a393a1a36e
  8. make_optimizer helper · level 1 · ran · our draft was wrong · 3c707eafb83ce730

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="2004.13922") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Language ModelingLanguage ModellingStock Market Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Stock Market Prediction Astock XLNET Chinese Accuray 61.14 #13 of 17 Archive leaderboard report
Stock Market Prediction Astock XLNET Chinese F1-score 61.19 #13 of 17 Archive leaderboard report
Stock Market Prediction Astock XLNET Chinese Precision 61.60 #13 of 17 Archive leaderboard report
Stock Market Prediction Astock XLNET Chinese Recall 61.09 #13 of 17 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: MacBERT

AdamAttentionAttention DropoutBERTDense ConnectionsDropoutLayer NormalizationLinear LayerLinear Warmup With Linear DecayMacBERTMulti-Head AttentionResidual ConnectionRoBERTaSoftmaxWeight 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