Papers › Glyce: Glyph-vectors for Chinese Character Representations

Glyce: Glyph-vectors for Chinese Character Representations

29 Jan 2019NeurIPS 2019 12arXiv:1901.10125archive 2025-07-28

Yuxian Meng, Wei Wu, Fei Wang, Xiaoya Li, Ping Nie, Fan Yin, Muyu Li, Qinghong Han, Xiaofei Sun, Jiwei Li

It is intuitive that NLP tasks for logographic languages like Chinese should benefit from the use of the glyph information in those languages. However, due to the lack of rich pictographic evidence in glyphs and the weak generalization ability of standard computer vision models on character data, an effective way to utilize the glyph information remains to be found. In this paper, we address this gap by presenting Glyce, the glyph-vectors for Chinese character representations. We make three major innovations: (1) We use historical Chinese scripts (e.g., bronzeware script, seal script, traditional Chinese, etc) to enrich the pictographic evidence in characters; (2) We design CNN structures (called tianzege-CNN) tailored to Chinese character image processing; and (3) We use image-classification as an auxiliary task in a multi-task learning setup to increase the model's ability to generalize. We show that glyph-based models are able to consistently outperform word/char ID-based models in a wide range of Chinese NLP tasks. We are able to set new state-of-the-art results for a variety of Chinese NLP tasks, including tagging (NER, CWS, POS), sentence pair classification, single sentence classification tasks, dependency parsing, and semantic role labeling. For example, the proposed model achieves an F1 score of 80.6 on the OntoNotes dataset of NER, +1.5 over BERT; it achieves an almost perfect accuracy of 99.8% on the Fudan corpus for text classification. Code found at https://github.com/ShannonAI/glyce.

PaperPDFConference PDFCodeCode Syntology ran

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 8 code samples harvested from 1 repository linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 8 samples from 1 repository, 8 ran (7 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.

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 8 samples that ran has no recorded date.

ShannonAI/glyce officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 8 samples, 8 ran (1 instrument-failed) · 0 unverified report
zhangyuwangumass/Glyph-based-Chinese-Character-Embedding mentioned on GitHubSyntology: 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.

Code Syntology ran Syntology

8 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 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.

2ran · honoured contract
1ran · our draft was wrong
5ran

Licence: 1 of the 8 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, 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 ShannonAI/glyce. “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.

ShannonAI/glyce official repository 8 samples, 8 ran (1 instrument-failed) · 0 unverified
swish in 258 papers
census: 14 implementations from 37 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
glyce/layers/bert_basic_model.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 0f786c407fb1ee4c · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded
channel_shuffle in 35 papers
census: 3 implementations from 7 papers, 2 distinct outputs on one shared input
glyce/glyph_cnn_models/downsample.py ran fingerprinted Apache-2.0 (permissive) · 68147246e5e691bf · report fixture: signature x:Tensor/4/float, groups:int/0/int · returned Tensor · level recorded 2026-09-25
channel_shuffle in 35 papers
census: 3 implementations from 7 papers, 2 distinct outputs on one shared input
glyce/glyph_cnn_models/utils.py ran fingerprinted Apache-2.0 (permissive) · 0438badc6adb3fb8 · report fixture: signature x:Tensor/4/float, groups:int/0/int · returned Tensor · level recorded 2026-09-25
count_params in 80 papers glyce/glyph_cnn_models/utils.py ran Apache-2.0 (permissive) · 483cee36456abbed · report fixture: signature conv:callable/0/? · returned int · level recorded 2026-09-25
gelu in 308 papers
census: 43 implementations from 74 papers, 6 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
glyce/layers/bert_basic_model.py ran · honoured contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 56a9ab06b860b180 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
gelu in 308 papers
census: 43 implementations from 74 papers, 6 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
glyce/glyph_cnn_models/glyph_group_cnn.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 50e1ffed03f484ec · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
masked_softmax in 51 papers
census: 10 implementations from 10 papers, 10 distinct outputs across 6 buckets, one shared input per bucket
glyce/glyph_cnn_models/self_attention.py ran fingerprinted Apache-2.0 (permissive) · 14797096cd0b979b · report fixture: signature vector:Tensor/2/float, mask:Tensor/2/float, dim:int/0/int · returned Tensor · level recorded 2026-09-25
weighted_sum in 11 papers glyce/glyph_cnn_models/self_attention.py ran fingerprinted Apache-2.0 (permissive) · 2f417d486bcad523 · report fixture: signature matrix:Tensor/3/float, attention:Tensor/2/float · returned Tensor · level recorded 2026-09-25

Tasks

Chinese Named Entity RecognitionChinese Semantic Role LabelingChinese Sentence Pair ClassificationChinese Word SegmentationClassificationDependency ParsingDocument ClassificationGeneral ClassificationImage ClassificationLanguage ModellingMachine TranslationMulti-Task LearningNERPOSPart-Of-Speech TaggingSemantic Role LabelingSemantic Textual SimilaritySentenceSentence ClassificationSentence-Pair ClassificationSentiment AnalysisText Classificationimage-classificationtext-classification

2 archive task tags without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Chinese Named Entity Recognition MSRA Glyce + BERT F1 95.54 #8 of 21 Archive leaderboard report
Chinese Named Entity Recognition MSRA Glyce + BERT Precision 95.57 #8 of 21 Archive leaderboard report
Chinese Named Entity Recognition MSRA Glyce + BERT Recall 95.51 #8 of 21 Archive leaderboard report
Chinese Named Entity Recognition OntoNotes 4 Glyce + BERT F1 80.62 #8 of 15 Archive leaderboard report
Chinese Named Entity Recognition OntoNotes 4 Glyce + BERT Precision 81.87 #8 of 15 Archive leaderboard report
Chinese Named Entity Recognition OntoNotes 4 Glyce + BERT Recall 81.4 #8 of 15 Archive leaderboard report
Chinese Named Entity Recognition Resume NER Glyce + BERT F1 96.54 #5 of 13 Archive leaderboard report
Chinese Named Entity Recognition Resume NER Glyce + BERT Precision 96.62 #5 of 13 Archive leaderboard report
Chinese Named Entity Recognition Resume NER Glyce + BERT Recall 96.48 #5 of 13 Archive leaderboard report
Chinese Named Entity Recognition Weibo NER Glyce + BERT F1 67.6 #9 of 18 Archive leaderboard report
Chinese Named Entity Recognition Weibo NER Glyce + BERT Precision 67.68 #9 of 18 Archive leaderboard report
Chinese Named Entity Recognition Weibo NER Glyce + BERT Recall 67.71 #9 of 18 Archive leaderboard report
Chinese Word Segmentation AS Glyce + BERT F1 96.7 #1 of 2 Archive leaderboard report
Chinese Word Segmentation AS Glyce + BERT Precision 96.6 #1 of 2 Archive leaderboard report
Chinese Word Segmentation AS Glyce + BERT Recall 96.8 #1 of 2 Archive leaderboard report
Chinese Word Segmentation CITYU Glyce + BERT F1 97.9 #2 of 2 Archive leaderboard report
Chinese Word Segmentation CITYU Glyce + BERT Precision 97.9 #2 of 2 Archive leaderboard report
Chinese Word Segmentation CITYU Glyce + BERT Recall 98 #2 of 2 Archive leaderboard report
Chinese Word Segmentation MSR Glyce + BERT F1 98.3 #5 of 6 Archive leaderboard report
Chinese Word Segmentation MSR Glyce + BERT Precision 98.2 #5 of 6 Archive leaderboard report
Chinese Word Segmentation MSR Glyce + BERT Recall 98.3 #5 of 6 Archive leaderboard report
Chinese Word Segmentation PKU Glyce + BERT F1 96.7 #2 of 4 Archive leaderboard report
Chinese Word Segmentation PKU Glyce + BERT Precision 97.1 #2 of 4 Archive leaderboard report
Chinese Word Segmentation PKU Glyce + BERT Recall 96.4 #2 of 4 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.

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