Papers › Big Bird: Transformers for Longer Sequences

Big Bird: Transformers for Longer Sequences

28 Jul 2020NeurIPS 2020 12arXiv:2007.14062archive 2025-07-28

Manzil Zaheer, Guru Guruganesh, Avinava Dubey, Joshua Ainslie, Chris Alberti, Santiago Ontanon, Philip Pham, Anirudh Ravula, Qifan Wang, Li Yang, Amr Ahmed

Transformers-based models, such as BERT, have been one of the most successful deep learning models for NLP. Unfortunately, one of their core limitations is the quadratic dependency (mainly in terms of memory) on the sequence length due to their full attention mechanism. To remedy this, we propose, BigBird, a sparse attention mechanism that reduces this quadratic dependency to linear. We show that BigBird is a universal approximator of sequence functions and is Turing complete, thereby preserving these properties of the quadratic, full attention model. Along the way, our theoretical analysis reveals some of the benefits of having O(1) global tokens (such as CLS), that attend to the entire sequence as part of the sparse attention mechanism. The proposed sparse attention can handle sequences of length up to 8x of what was previously possible using similar hardware. As a consequence of the capability to handle longer context, BigBird drastically improves performance on various NLP tasks such as question answering and summarization. We also propose novel applications to genomics data.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2007.14062")

Code

Syntology Ran 10 of 15 code samples harvested from 3 repositories linked to this paper; 5 have no recorded run. Of those that ran: 1 ran · honoured contract; 5 ran · our draft was wrong; 3 ran · fixture could not drive it; 1 ran with no contract checked.

By repository: official repository: 2 samples from 1 repository, 1 ran; community (archive-listed): 13 samples from 2 repositories, 9 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

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

facebookresearch/xformers mentioned on GitHubpytorch report
huggingface/transformers mentioned on GitHubpytorch report
mim-solutions/bert_for_longer_texts mentioned on GitHubpytorch report
mim-solutions/roberta_for_longer_texts mentioned on GitHubpytorchNOASSERTION report
monologg/kobigbird mentioned on GitHubtf report
sajjjadayobi/ParsBigBird mentioned on GitHubAGPL-3.0 report
sergeykramp/mthesis-bigbird-embeddings mentioned on GitHubpytorch report
thefonseca/factorsum mentioned on GitHubpytorch report
pwc-1/Paper-8 mindspore report
pwc-1/Paper-8 mindspore 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

15 samples harvested; 10 ran; 1 honoured the contract we drafted; 5 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
5ran · our draft was wrong
3ran · fixture could not drive it
1ran
5unverified

Licence: 11 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. 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; each sample names its own and says which. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

create_rand_mask_from_inputs google-research/bigbird/bigbird/core/attention.py official repository ran · fixture could not drive it Apache-2.0 (permissive) · 44d0dd1eff48b3db · report
bigbird_block_sparse_attention google-research/bigbird/bigbird/core/attention.py official repository unverified Apache-2.0 (permissive) · 0d09b5689924a10b · report
InconsistentSplittingParamsException mim-solutions/bert_for_longer_texts/belt_nlp/splitting.py community (archive-listed) ran · metamorphic tier: deterministic licence not identified · pointer only · e4b0ec678a1f3059 · report
create_rand_mask_from_inputs monologg/kobigbird/pretrain/kobigbird/attention.py community (archive-listed) ran · fixture could not drive it Apache-2.0 (permissive) · 2c5945c3b5a80279 · report
split_overlapping mim-solutions/bert_for_longer_texts/belt_nlp/splitting.py community (archive-listed) ran · fixture could not drive it licence not identified · pointer only · c91a4a5114716579 · report
split_tokens_into_smaller_chunks mim-solutions/bert_for_longer_texts/belt_nlp/splitting.py community (archive-listed) ran · our draft was wrong licence not identified · pointer only · 0ce3135e26fafb14 · report
stack_tokens_from_all_chunks mim-solutions/bert_for_longer_texts/belt_nlp/splitting.py community (archive-listed) ran · our draft was wrong licence not identified · pointer only · 15b2fccc82d0a62a · report
tokenize_text_with_truncation mim-solutions/bert_for_longer_texts/belt_nlp/splitting.py community (archive-listed) ran · our draft was wrong licence not identified · pointer only · 4123d6b63df245f2 · report
tokenize_whole_text mim-solutions/bert_for_longer_texts/belt_nlp/splitting.py community (archive-listed) ran · our draft was wrong licence not identified · pointer only · 316d08e3b6936972 · report
transform_list_of_texts mim-solutions/bert_for_longer_texts/belt_nlp/splitting.py community (archive-listed) ran · our draft was wrong licence not identified · pointer only · 41d96f44b38351ac · report
transform_single_text mim-solutions/bert_for_longer_texts/belt_nlp/splitting.py community (archive-listed) ran · honoured contract licence not identified · pointer only · 4d240665f4cb4490 · report
add_padding_tokens mim-solutions/bert_for_longer_texts/belt_nlp/splitting.py community (archive-listed) unverified licence not identified · pointer only · 4603a2fe10eb193d · report
add_special_tokens_at_beginning_and_end mim-solutions/bert_for_longer_texts/belt_nlp/splitting.py community (archive-listed) unverified licence not identified · pointer only · dd7b545b8b9f7fed · report
bigbird_block_sparse_attention monologg/kobigbird/pretrain/kobigbird/attention.py community (archive-listed) unverified Apache-2.0 (permissive) · b18d818e15d8f5f2 · report
check_split_parameters_consistency mim-solutions/bert_for_longer_texts/belt_nlp/splitting.py community (archive-listed) unverified licence not identified · pointer only · e219be299ea45b2d · report

Tasks

Linguistic AcceptabilityNatural Language InferenceQuestion AnsweringSemantic Textual SimilarityText ClassificationText Summarization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Document Summarization BBC XSum BigBird-Pegasus ROUGE-1 47.12 #1 of 1 Archive leaderboard report
Document Summarization BBC XSum BigBird-Pegasus ROUGE-2 24.05 #1 of 1 Archive leaderboard report
Document Summarization BBC XSum BigBird-Pegasus ROUGE-L 38.8 #1 of 1 Archive leaderboard report
Document Summarization CNN / Daily Mail BigBird-Pegasus ROUGE-1 43.84 #10 of 26 Archive leaderboard report
Document Summarization CNN / Daily Mail BigBird-Pegasus ROUGE-2 21.11 #10 of 26 Archive leaderboard report
Document Summarization CNN / Daily Mail BigBird-Pegasus ROUGE-L 40.74 #10 of 26 Archive leaderboard report
Linguistic Acceptability CoLA BigBird Accuracy 58.5% #32 of 43 Archive leaderboard report
Natural Language Inference MultiNLI BigBird Matched 87.5 #22 of 67 Archive leaderboard report
Natural Language Inference QNLI BigBird Accuracy 92.2% #26 of 43 Archive leaderboard report
Natural Language Inference RTE BigBird Accuracy 75.0% #44 of 90 Archive leaderboard report
Question Answering HotpotQA BigBird-etc ANS-F1 0.755 #2 of 72 Archive leaderboard report
Question Answering HotpotQA BigBird-etc JOINT-F1 0.736 #2 of 72 Archive leaderboard report
Question Answering HotpotQA BigBird-etc SUP-F1 0.891 #2 of 72 Archive leaderboard report
Question Answering Quora Question Pairs BigBird Accuracy 88.6% #15 of 19 Archive leaderboard report
Question Answering TriviaQA BigBird-etc F1 80.9 #49 of 56 Archive leaderboard report
Question Answering WikiHop BigBird-etc Test 82.3 #1 of 9 Archive leaderboard report
Semantic Textual Similarity MRPC BigBird F1 91.5 #38 of 45 Archive leaderboard report
Semantic Textual Similarity STS Benchmark BigBird Spearman Correlation .878 #39 of 66 Archive leaderboard report
Sentiment Analysis SST-2 Binary classification BigBird Accuracy 94.6 #34 of 87 Archive leaderboard report
Text Classification Arxiv HEP-TH citation graph BigBird Accuracy 92.31 #1 of 1 Archive leaderboard report
Text Classification Hyperpartisan BigBird Accuracy 92.2 #1 of 1 Archive leaderboard report
Text Classification Patents BigBird Accuracy 69.3 #1 of 1 Archive leaderboard report
Text Classification Yelp-5 BigBird Accuracy 72.16% #3 of 7 Archive leaderboard report
Text Summarization BigPatent BigBird-Pegasus ROUGE-1 60.64 #2 of 2 Archive leaderboard report
Text Summarization BigPatent BigBird-Pegasus ROUGE-2 42.46 #2 of 2 Archive leaderboard report
Text Summarization BigPatent BigBird-Pegasus ROUGE-L 50.01 #2 of 2 Archive leaderboard report
Text Summarization Pubmed BigBird-Pegasus ROUGE-1 46.32 #15 of 29 Archive leaderboard report
Text Summarization Pubmed BigBird-Pegasus ROUGE-2 20.65 #15 of 29 Archive leaderboard report
Text Summarization Pubmed BigBird-Pegasus ROUGE-L 42.33 #15 of 29 Archive leaderboard report
Text Summarization arXiv BigBird-Pegasus ROUGE-1 46.63 #1 of 1 Archive leaderboard report
Text Summarization arXiv BigBird-Pegasus ROUGE-2 19.02 #1 of 1 Archive leaderboard report
Text Summarization arXiv BigBird-Pegasus ROUGE-L 41.77 #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

Introduced by this paper: BigBird

BigBird

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