Papers › Revisiting Pre-Trained Models for Chinese Natural Language Processing
Revisiting Pre-Trained Models for Chinese Natural Language Processing
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
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):
get_harvested_code_for_paper(arxiv_id="2004.13922")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2004.13922", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2004.13922")
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:
- gaussic/text-classification-cnn-rnn, found in paper text by Syntology: Syntology's graph links these samples to Convolutional Neural Networks for Sentence Classification (arXiv:1408.5882; that paper's own run record: 53 ran (of which 0 constructed an object rather than computing a result; 40 with no instrument failure: 6 honoured, 1 violated, 33 with no contract checked; 13 where Syntology's instrument failed) · 24 unverified); nothing checks that they implement this paper's method.
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.
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.
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.
49538ded4b211b0d · report
fixture: returned FocalLoss · level recorded 2026-09-22 bc8cd524a10a5326 · report
fixture: signature results:list/1/tuple, logger:Logger/0/? · returned tuple · level recorded 2026-09-22 731b5640fb2a2a52 · report
fixture: signature results:list/1/tuple, logger:Logger/0/? · returned tuple · level recorded 2026-09-22 3c707eafb83ce730 · report
fixture: signature cfg:Config/0/?, model:callable/0/? · returned SGD · level recorded 2026-09-22 cfac541eefda5168 · report
af8425a9c3022046 · report
f5ffeb1faccdd442 · report
699577a393a1a36e · report
b03d45af664a39e3 · report
fixture: signature values:list/1/int · returned Feature · level recorded 2026-09-26 b71224516be1ddfa · report
fixture: signature s1:str/0/str, s2:str/0/str · returned tuple · level recorded 2026-09-24 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 b2dfae5f1625da67 · report
fixture: signature activation_string:str/0/str · returned function · level recorded 2026-09-24 cb34c9c201e23b66 · report
fixture: signature tvars:list/1/ResourceVariable, init_checkpoint:str/0/str, prefix:str/0/str · returned tuple · level recorded 2026-09-24 2ac9d5179c0b5c85 · report
5a2e0cd001c9f26b · report
6b2a8f1c93d0b071 · report
fixture: signature gpu:int/0/int, ps_dev:str/0/str · returned function · level recorded 2026-09-25 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 b9e225229ba459c3 · report
fixture: signature is_training:bool/0/bool, is_finetune:bool/0/bool, FLAGS:FLAGSConfig/0/? · returned RunConfig · level recorded 2026-09-24 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 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 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 aa6bc32d9c17a2f1 · report
fixture: signature s:str/0/str · returned list · level recorded 2026-09-22 e91c44f5680827e2 · report
fixture: signature dataset:list/1/dict · returned dict · level recorded 2026-09-22 6a96435eba311b08 · report
fixture: signature s:str/0/str · returned str · level recorded 2026-09-22 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 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 0e5615f8994003cf · report
fixture: signature text:str/0/str · returned str · level recorded 2026-09-26 0e3f1e158da4c3b8 · report
c09b2ad22d30dc58 · report
5abf0267f0fc7514 · report
aab5156ced02aa8a · report
7b1d9794b90b3ae2 · report
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.
- MacBert4Csc entry · level 0 · unverified ·
f5ffeb1faccdd442 - CscTrainingModel helper · level 0 · unverified ·
af8425a9c3022046 - FocalLoss loss · level 1 · ran ·
49538ded4b211b0d - BaseTrainingEngine helper · level 0 · unverified ·
cfac541eefda5168 - compute_corrector_prf helper · level 1 · ran · honoured contract ·
bc8cd524a10a5326 - compute_sentence_level_prf helper · level 1 · ran · honoured contract ·
731b5640fb2a2a52 - build_lr_scheduler helper · level 0 · unverified ·
699577a393a1a36e - 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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 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
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