Papers › CharacterBERT: Reconciling ELMo and BERT for Word-Level Open-Vocabulary...

CharacterBERT: Reconciling ELMo and BERT for Word-Level Open-Vocabulary Representations From Characters

20 Oct 2020COLING 2020 8arXiv:2010.10392archive 2025-07-28

Hicham El Boukkouri, Olivier Ferret, Thomas Lavergne, Hiroshi Noji, Pierre Zweigenbaum, Junichi Tsujii

Due to the compelling improvements brought by BERT, many recent representation models adopted the Transformer architecture as their main building block, consequently inheriting the wordpiece tokenization system despite it not being intrinsically linked to the notion of Transformers. While this system is thought to achieve a good balance between the flexibility of characters and the efficiency of full words, using predefined wordpiece vocabularies from the general domain is not always suitable, especially when building models for specialized domains (e.g., the medical domain). Moreover, adopting a wordpiece tokenization shifts the focus from the word level to the subword level, making the models conceptually more complex and arguably less convenient in practice. For these reasons, we propose CharacterBERT, a new variant of BERT that drops the wordpiece system altogether and uses a Character-CNN module instead to represent entire words by consulting their characters. We show that this new model improves the performance of BERT on a variety of medical domain tasks while at the same time producing robust, word-level and open-vocabulary representations.

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

No sample from the archive's official repository (helboukkouri/character-bert) is linked to this paper; the 8 samples below come from 1 community repository. Syntology harvested code from helboukkouri/character-bert for another paper.

helboukkouri/character-bert: Syntology's graph links these samples to Deep contextualized word representations (arXiv:1802.05365; that paper's own run record: 30 ran (of which 12 constructed an object rather than computing a result; 24 with no instrument failure: 2 honoured, 0 violated, 22 with no contract checked; 6 where Syntology's instrument failed) · 28 unverified); nothing checks that they implement this paper's method.

Syntology 8 code samples harvested from 1 repository linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 8 samples from 1 repository, 6 ran (3 with no instrument failure; 3 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.

helboukkouri/character-bert officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep contextualized word representations (arXiv:1802.05365; that paper's own run record: 30 ran (of which 12 constructed an object rather than computing a result; 24 with no instrument failure: 2 honoured, 0 violated, 22 with no contract checked; 6 where Syntology's instrument failed) · 28 unverified); nothing checks that they implement this paper's method. report
IMPLabUniPr/UniParma-at-semeval-2021-task-5 mentioned on GitHubpytorchApache-2.0Syntology: 8 samples, 6 ran (3 instrument-failed) · 2 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

8 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 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.

2ran · honoured contract
3ran · our draft was wrong
1ran
2unverified

Licence: 4 of the 8 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 IMPLabUniPr/UniParma-at-semeval-2021-task-5. “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.

IMPLabUniPr/UniParma-at-semeval-2021-task-5 community (archive-listed) 8 samples, 6 ran (3 instrument-failed) · 2 unverified
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
transformers/modeling_bert.py ran · honoured contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 211753ba29188d4e · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
gelu_new in 55 papers
census: 3 implementations from 7 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
transformers/modeling_bert.py ran · honoured contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 77601724cad03f95 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
load_tf_weights_in_bert in 135 papers transformers/modeling_bert.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 0c145728a35789fa · report fixture: signature model:callable/0/?, config:Config/0/?, tf_checkpoint_path:str/0/str · returned BertModel · level recorded 2026-09-22
squash in 30 papers
census: 8 implementations from 5 papers, 4 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 2 of 2, arg 1: rank 3, kind float, dtype float32
modeling/layer_ae.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 5abcd8c6705f2368 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
squash_v1 modeling/layer_ae.py ran fingerprinted Apache-2.0 (permissive) · d4ec0b3bf4bf193d · report fixture: signature x:Tensor/3/float, axis:int/0/int · returned Tensor · level recorded 2026-09-24
tile in 109 papers
census: 5 implementations from 7 papers, 4 distinct outputs across 3 buckets, one shared input per bucket
transformers/modeling_beam_search.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · a878dc3112f9ce9e · report fixture: signature x:Tensor/2/float, count:int/0/int, dim:int/0/int · returned Tensor · level recorded 2026-09-24
get_confirm_token in 41 papers download.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · 135b3dc835ffe6ad · report
load_classification_dataset data.py unverified Apache-2.0 (permissive) · 9ab72e873c485839 · report

Tasks

Clinical Concept ExtractionDrug–drug Interaction ExtractionNatural Language InferenceRelation ExtractionSemantic Similarity

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Clinical Concept Extraction 2010 i2b2/VA CharacterBERT (base, medical) Exact Span F1 89.24 #2 of 5 Archive leaderboard report
Drug–drug Interaction Extraction DDI extraction 2013 corpus CharacterBERT (base, medical) Micro F1 80.38 #9 of 10 Archive leaderboard report
Natural Language Inference MedNLI CharacterBERT (base, medical) Accuracy 84.95 #4 of 7 Archive leaderboard report
Relation Extraction ChemProt CharacterBERT (base, medical) Micro F1 73.44 #13 of 13 Archive leaderboard report
Semantic Similarity ClinicalSTS CharacterBERT (base, medical, ensemble) Pearson Correlation 85.62 #1 of 1 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

Absolute Position EncodingsAdamAttentionAttention DropoutBERTBPECharacterBERTDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformerWeight 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