Papers › BioBERT: a pre-trained biomedical language representation model for biomedical text mining

BioBERT: a pre-trained biomedical language representation model for biomedical text mining

25 Jan 2019arXiv:1901.08746archive 2025-07-28

Jinhyuk Lee, Wonjin Yoon, Sungdong Kim, Donghyeon Kim, Sunkyu Kim, Chan Ho So, Jaewoo Kang

Biomedical text mining is becoming increasingly important as the number of biomedical documents rapidly grows. With the progress in natural language processing (NLP), extracting valuable information from biomedical literature has gained popularity among researchers, and deep learning has boosted the development of effective biomedical text mining models. However, directly applying the advancements in NLP to biomedical text mining often yields unsatisfactory results due to a word distribution shift from general domain corpora to biomedical corpora. In this article, we investigate how the recently introduced pre-trained language model BERT can be adapted for biomedical corpora. We introduce BioBERT (Bidirectional Encoder Representations from Transformers for Biomedical Text Mining), which is a domain-specific language representation model pre-trained on large-scale biomedical corpora. With almost the same architecture across tasks, BioBERT largely outperforms BERT and previous state-of-the-art models in a variety of biomedical text mining tasks when pre-trained on biomedical corpora. While BERT obtains performance comparable to that of previous state-of-the-art models, BioBERT significantly outperforms them on the following three representative biomedical text mining tasks: biomedical named entity recognition (0.62% F1 score improvement), biomedical relation extraction (2.80% F1 score improvement) and biomedical question answering (12.24% MRR improvement). Our analysis results show that pre-training BERT on biomedical corpora helps it to understand complex biomedical texts. We make the pre-trained weights of BioBERT freely available at https://github.com/naver/biobert-pretrained, and the source code for fine-tuning BioBERT available at https://github.com/dmis-lab/biobert.

PaperPDFCodeCode 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

The archive's official repositories (dmis-lab/biobert, naver/biobert-pretrained) were not harvested; the 24 samples below come from 3 community repositories, and 1 more is identical to code Syntology harvested from another paper's repository.

Syntology 25 code samples: 24 from 3 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 25: 15 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 10 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 24 samples from 3 repositories, 14 ran (10 with no instrument failure; 4 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. 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 5 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.

19 repositories listed; official and paper-mentioned ones first.

dmis-lab/biobert officialmentioned in papermentioned on GitHubtfNOASSERTIONSyntology: not harvested report
naver/biobert-pretrained officialmentioned in papermentioned on GitHubSyntology: not harvested report
EmilyAlsentzer/clinicalBERT mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
ManasRMohanty/DS5500-capstone mentioned on GitHubpytorchSyntology: not harvested report
MeRajat/SolvingAlmostAnythingWithBert mentioned on GitHubpytorchSyntology: not harvested report
ardakdemir/my_bert_ner mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
charles9n/bert-sklearn mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (arXiv:1810.04805; that paper's own run record: 300 ran (of which 75 constructed an object rather than computing a result; 234 with no instrument failure: 18 honoured, 5 violated, 211 with no contract checked; 66 where Syntology's instrument failed) · 359 unverified); nothing checks that they implement this paper's method. report
cypressd1999/FYP_2021 mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ALBERT: A Lite BERT for Self-supervised Learning of Language Representations (arXiv:1909.11942; that paper's own run record: 81 ran (of which 17 constructed an object rather than computing a result; 56 with no instrument failure: 4 honoured, 0 violated, 52 with no contract checked; 25 where Syntology's instrument failed) · 45 unverified); nothing checks that they implement this paper's method. report
dmis-lab/bern mentioned on GitHubtfBSD-2-ClauseSyntology: 20 samples, 10 ran (3 instrument-failed) · 10 unverified report
hieudepchai/BERT_IE mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
jpablou/Matching-The-Blanks-Ths mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ALBERT: A Lite BERT for Self-supervised Learning of Language Representations (arXiv:1909.11942; that paper's own run record: 81 ran (of which 17 constructed an object rather than computing a result; 56 with no instrument failure: 4 honoured, 0 violated, 52 with no contract checked; 25 where Syntology's instrument failed) · 45 unverified); nothing checks that they implement this paper's method. report
kuldeep7688/BioMedicalBertNer mentioned on GitHubpytorchSyntology: not harvested report
mocherson/aki_bert mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (arXiv:1810.04805; that paper's own run record: 300 ran (of which 75 constructed an object rather than computing a result; 234 with no instrument failure: 18 honoured, 5 violated, 211 with no contract checked; 66 where Syntology's instrument failed) · 359 unverified); nothing checks that they implement this paper's method. report
phucdev/TL_Bio_RE mentioned on GitHubtfApache-2.0Syntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
plkmo/BERT-Relation-Extraction mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
rahul-1996/KGraphs-QA mentioned on GitHubpytorchSyntology: not harvested report
re-search/DocProduct mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Attention Is All You Need (arXiv:1706.03762; that paper's own run record: 610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified) and BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (arXiv:1810.04805; that paper's own run record: 300 ran (of which 75 constructed an object rather than computing a result; 234 with no instrument failure: 18 honoured, 5 violated, 211 with no contract checked; 66 where Syntology's instrument failed) · 359 unverified); nothing checks that they implement this paper's method. report
dagshub.com/Dean/BioBERT-DAGsHub Syntology: not harvested report
ncbi-nlp/NCBI_BERT tfNOASSERTIONSyntology: 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

25 samples harvested: 15 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 10 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.

1ran · honoured contract
4ran · our draft was wrong
10ran
10unverified

Licence: 3 of the 25 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 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. 1 sample is listed last, in a group without a repository. “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.

EmilyAlsentzer/clinicalBERT community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
convert_examples_to_features in 134 papers downstream_tasks/run_classifier.py ran · our draft was wrong MIT (permissive) · 06b922528ebf4e7d · report fixture: signature examples:list/1/Example, label_list:list/1/str, max_seq_length:int/0/int, tokenizer:MockTokenizer/0/? · returned list · level recorded 2026-09-22
dmis-lab/bern community (archive-listed) 20 samples, 10 ran (3 instrument-failed) · 10 unverified
convert_to_unicode in 40 papers biobert_ner/tokenization.py ran · our draft was wrong fingerprinted BSD-2-Clause (permissive) here; the stored copy is pointer only · 1923fc05163d207d · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-22
count_entities server.py ran BSD-2-Clause (permissive) · cb11382d4dfba32c · report fixture: signature data:list/1/dict · returned int · level recorded 2026-09-24
example_input_fn biobert_ner/fast_predict2.py ran BSD-2-Clause (permissive) · 9f260f0f69ef7785 · report fixture: signature generator:callable/0/? · returned function · level recorded 2026-09-24
get_activation in 218 papers biobert_ner/modeling.py ran · our draft was wrong BSD-2-Clause (permissive) · 2dc172f4dc0c745c · report fixture: signature activation_string:str/0/str · returned function · level recorded 2026-09-22
get_stats in 37 papers service_checker.py ran BSD-2-Clause (permissive) · 549c4d310160c2df · report fixture: signature lst:list/1/float, batch_size:NoneType/0/? · returned tuple · level recorded 2026-09-24
input_form biobert_ner/ops.py ran BSD-2-Clause (permissive) · 07b9d1982202e17a · report fixture: signature sent_data:dict/0/? · returned dict · level recorded 2026-09-24
isInt biobert_ner/ops.py ran BSD-2-Clause (permissive) · 4a5aed3ff2a20598 · report fixture: signature string:str/0/str · returned bool · level recorded 2026-09-24
json_to_sent biobert_ner/ops.py ran BSD-2-Clause (permissive) · 129d9b786094b9f2 · report fixture: signature data:list/1/dict, is_raw_text:bool/0/bool · returned dict · level recorded 2026-09-24
printable_text in 36 papers biobert_ner/tokenization.py ran · our draft was wrong BSD-2-Clause (permissive) · 0e5615f8994003cf · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-26
run_command in 61 papers utils.py ran BSD-2-Clause (permissive) · 7db82cce6fd97e13 · report fixture: signature command:list/1/str, cwd:str/0/str · returned int · level recorded 2026-09-24
file_based_input_fn_builder in 16 papers biobert_ner/run_ner.py unverified BSD-2-Clause (permissive) · 925eb3d68d846286 · report
gelu in 308 papers
census: 43 implementations from 74 papers, 6 distinct outputs on one shared input
biobert_ner/modeling.py unverified BSD-2-Clause (permissive) · 6558b9f62bb65244 · report
get_assignment_map_from_checkpoint in 32 papers biobert_ner/modeling.py unverified BSD-2-Clause (permissive) here; the stored copy is pointer only · 50958618b65e514e · report
get_pubmed_xml download.py unverified BSD-2-Clause (permissive) · d99e3a923de61df6 · report
load_vocab in 107 papers biobert_ner/tokenization.py unverified BSD-2-Clause (permissive) · ff83ccc8b0b6462d · report
pubtator2dict_list convert.py unverified BSD-2-Clause (permissive) · 8efd15b4de560c86 · report
pubtatorstr2dict_list convert.py unverified BSD-2-Clause (permissive) · abf03461f901b84e · report
query in 11 papers utils.py unverified BSD-2-Clause (permissive) · 63af112374694328 · report
query_raw utils.py unverified BSD-2-Clause (permissive) · 038a5858855dfabd · report
tell_inputfile server.py unverified BSD-2-Clause (permissive) · 183875341edd669d · report
phucdev/TL_Bio_RE community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
convert_examples_to_features in 134 papers tlbiore/dataset_readers/readers.py ran Apache-2.0 (permissive) · 13645454ee9a48df · report fixture: signature examples:list/1/MockExample, max_seq_len:int/0/int, tokenizer:MockTokenizer/0/?, cls_token:str/0/str, cls_token_segment_id:int/0/int, sep_token:str/0/str, pad_token:int/0/int, pad_token_segment_id:int/0/int, sequence_a_segment_id:int/0/int, add_sep_token:bool/0/bool, mask_padding_with_zero:bool/0/bool, use_positional_markers:bool/0/bool · returned list · level recorded 2026-09-24
get_label in 36 papers tlbiore/utils.py ran Apache-2.0 (permissive) · 0f7620720c0761a8 · report fixture: signature args:Args/0/? · returned list · level recorded 2026-09-25
get_predict_pair_ids tlbiore/utils.py ran Apache-2.0 (permissive) · 76656b04052ade73 · report fixture: signature args:Args/0/? · returned Series · level recorded 2026-09-24
Repository not located 1 sample, 1 ran (0 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
repository not located ran · honoured contract fingerprinted licence of this copy not recorded · eb725d5794b15f6b · report fixture: signature out:ndarray/2/float, labels:ndarray/1/int · returned int64 · level recorded 2026-09-22

Tasks

Drug–drug Interaction ExtractionFew-Shot LearningLanguage ModellingMedical Named Entity RecognitionMedical Relation ExtractionNamed Entity RecognitionNamed Entity Recognition (NER)Question AnsweringRelation ExtractionRepresentation LearningSentence ClassificationZero-Shot Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Drug–drug Interaction Extraction DDI extraction 2013 corpus BioBERT F1 0.8088 #4 of 10 Archive leaderboard report
Drug–drug Interaction Extraction DDI extraction 2013 corpus BioBERT Micro F1 80.88 #4 of 10 Archive leaderboard report
Few-Shot Learning MedConceptsQA dmis-lab/biobert-v1.1 Accuracy 25.458 #6 of 12 Archive leaderboard report
Named Entity Recognition (NER) JNLPBA BioBERT F1 77.59 #13 of 17 Archive leaderboard report
Named Entity Recognition (NER) NCBI-disease BioBERT F1 89.71 #1 of 26 Archive leaderboard report
Named Entity Recognition (NER) Species-800 BioBERT F1 75.31 #1 of 4 Archive leaderboard report
Question Answering MedQA BioBERT (large) Accuracy 36.7 #23 of 27 Archive leaderboard report
Question Answering MedQA BioBERT (base) Accuracy 34.1 #24 of 27 Archive leaderboard report
Relation Extraction ChemProt BioBERT F1 76.46 #8 of 13 Archive leaderboard report
Representation Learning SciDocs BioBERT Avg. 58.8 #6 of 7 Archive leaderboard report
Zero-Shot Learning MedConceptsQA dmis-lab/biobert-v1.1 Accuracy 26.151 #3 of 13 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

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