Papers › BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key...

BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents

10 Aug 2021arXiv:2108.04539archive 2025-07-28

Teakgyu Hong, Donghyun Kim, Mingi Ji, Wonseok Hwang, Daehyun Nam, Sungrae Park

Key information extraction (KIE) from document images requires understanding the contextual and spatial semantics of texts in two-dimensional (2D) space. Many recent studies try to solve the task by developing pre-trained language models focusing on combining visual features from document images with texts and their layout. On the other hand, this paper tackles the problem by going back to the basic: effective combination of text and layout. Specifically, we propose a pre-trained language model, named BROS (BERT Relying On Spatiality), that encodes relative positions of texts in 2D space and learns from unlabeled documents with area-masking strategy. With this optimized training scheme for understanding texts in 2D space, BROS shows comparable or better performance compared to previous methods on four KIE benchmarks (FUNSD, SROIE*, CORD, and SciTSR) without relying on visual features. This paper also reveals two real-world challenges in KIE tasks-(1) minimizing the error from incorrect text ordering and (2) efficient learning from fewer downstream examples-and demonstrates the superiority of BROS over previous methods. Code is available at https://github.com/clovaai/bros.

PaperPDFCodeCode 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="2108.04539")

Code

Syntology Ran 2 of 13 code samples harvested from 1 repository linked to this paper; 11 have no recorded run. Of those that ran: 2 ran · our draft was wrong.

By repository: official repository: 13 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

clovaai/bros officialmentioned in papermentioned on GitHubpytorchApache-2.0 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

13 samples harvested; 2 ran; 0 honoured the contract we drafted; 11 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.

2ran · our draft was wrong
11unverified

Licence: 0 of the 13 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 clovaai/bros. “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.

whitespace_tokenize clovaai/bros/bros/tokenization_bros.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · cf9ffa02a42184af · report
load_vocab clovaai/bros/bros/tokenization_bros.py official repository ran · our draft was wrong Apache-2.0 (permissive) · e7fbc7a74a3457c7 · report
do_eval_step clovaai/bros/lightning_modules/bros_bies_module.py official repository unverified Apache-2.0 (permissive) · 3944c09a44634e37 · report
do_eval_step clovaai/bros/lightning_modules/bros_bio_module.py official repository unverified Apache-2.0 (permissive) · b0682ddacb993e88 · report
do_eval_step clovaai/bros/lightning_modules/bros_spade_module.py official repository unverified Apache-2.0 (permissive) · a19d5a58a6632b6a · report
do_eval_step clovaai/bros/lightning_modules/bros_spade_rel_module.py official repository unverified Apache-2.0 (permissive) · a24cbc913ce1517c · report
eval_ee_bio_batch clovaai/bros/lightning_modules/bros_bio_module.py official repository unverified Apache-2.0 (permissive) · 62ed443571cf13ef · report
eval_ee_bio_example clovaai/bros/lightning_modules/bros_bio_module.py official repository unverified Apache-2.0 (permissive) · 1bfd47528da7b59e · report
eval_ee_spade_batch clovaai/bros/lightning_modules/bros_spade_module.py official repository unverified Apache-2.0 (permissive) · 0e5e7de5c6b14651 · report
eval_ee_spade_example clovaai/bros/lightning_modules/bros_spade_module.py official repository unverified Apache-2.0 (permissive) · cf68c6ab08d0c012 · report
eval_el_spade_batch clovaai/bros/lightning_modules/bros_spade_rel_module.py official repository unverified Apache-2.0 (permissive) · ffb90147092f9680 · report
eval_el_spade_example clovaai/bros/lightning_modules/bros_spade_rel_module.py official repository unverified Apache-2.0 (permissive) · 8e888f85f35bcb89 · report
get_label_map clovaai/bros/lightning_modules/bros_bies_module.py official repository unverified Apache-2.0 (permissive) · 07564a0cc69b377b · report

Tasks

Key Information ExtractionLanguage ModelingLanguage ModellingOptical Character Recognition (OCR)Relation Extraction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Relation Extraction FUNSD BROS F1 77.01 #7 of 9 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