Papers › DocBERT: BERT for Document Classification

DocBERT: BERT for Document Classification

17 Apr 2019arXiv:1904.08398archive 2025-07-28

Ashutosh Adhikari, Achyudh Ram, Raphael Tang, Jimmy Lin

We present, to our knowledge, the first application of BERT to document classification. A few characteristics of the task might lead one to think that BERT is not the most appropriate model: syntactic structures matter less for content categories, documents can often be longer than typical BERT input, and documents often have multiple labels. Nevertheless, we show that a straightforward classification model using BERT is able to achieve the state of the art across four popular datasets. To address the computational expense associated with BERT inference, we distill knowledge from BERT-large to small bidirectional LSTMs, reaching BERT-base parity on multiple datasets using 30x fewer parameters. The primary contribution of our paper is improved baselines that can provide the foundation for future work.

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="1904.08398")

Code

Syntology Ran 0 of 14 code samples harvested from 2 repositories linked to this paper; 14 have no recorded run.

By repository: official repository: 7 samples from 1 repository, 0 ran; community (archive-listed): 7 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

castorini/hedwig officialmentioned in papermentioned on GitHubpytorchApache-2.0 report
dki-lab/covid19-classification mentioned 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

14 samples harvested; 0 ran; 0 honoured the contract we drafted; 14 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.

14unverified

Licence: 0 of the 14 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 2 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.

char_quantize castorini/hedwig/datasets/ag_news.py official repository unverified Apache-2.0 (permissive) · 2687bbd8d00ccade · report
clean_string castorini/hedwig/datasets/ag_news.py official repository unverified Apache-2.0 (permissive) · 055cfc782a4a7f7a · report
clean_string castorini/hedwig/datasets/imdb_torchtext.py official repository unverified Apache-2.0 (permissive) · 4488684e7b9d2033 · report
process_labels castorini/hedwig/datasets/aapd.py official repository unverified Apache-2.0 (permissive) · 19822471f0ab141f · report
process_labels castorini/hedwig/datasets/ag_news.py official repository unverified Apache-2.0 (permissive) · c3168b8fd9f4e646 · report
process_labels castorini/hedwig/datasets/imdb_torchtext.py official repository unverified Apache-2.0 (permissive) · b7b8e5514548bb67 · report
process_labels castorini/hedwig/datasets/ohsumed.py official repository unverified Apache-2.0 (permissive) · ddf92ba4082dc557 · report
clean_string dki-lab/covid19-classification/hedwig/datasets/litcovid.py community (archive-listed) unverified Apache-2.0 (permissive) · 2c0a5cc710857b97 · report
clean_string dki-lab/covid19-classification/hedwig/datasets/reuters.py community (archive-listed) unverified Apache-2.0 (permissive) · 17e08d7d57300508 · report
clean_string dki-lab/covid19-classification/hedwig/datasets/robust45.py community (archive-listed) unverified Apache-2.0 (permissive) · 2036a64496afb96e · report
generate_ngrams dki-lab/covid19-classification/hedwig/datasets/litcovid.py community (archive-listed) unverified Apache-2.0 (permissive) · bfab8ed9d3ecab22 · report
process_labels dki-lab/covid19-classification/hedwig/datasets/robust45.py community (archive-listed) unverified Apache-2.0 (permissive) · ce45ec6885c24577 · report
split_sents dki-lab/covid19-classification/hedwig/datasets/litcovid.py community (archive-listed) unverified Apache-2.0 (permissive) · b6bc698ac705604f · report
split_sents dki-lab/covid19-classification/hedwig/datasets/robust45.py community (archive-listed) unverified Apache-2.0 (permissive) · 0547489e02ef3fbf · report

Tasks

ClassificationDocument ClassificationGeneral ClassificationSentiment AnalysisText Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Document Classification AAPD KD-LSTMreg F1 72.9 #1 of 2 Archive leaderboard report
Document Classification Reuters-21578 KD-LSTMreg F1 88.9 #6 of 8 Archive leaderboard report
Document Classification Yelp-14 KD-LSTMreg Accuracy 69.4 #1 of 1 Archive leaderboard report
Text Classification arXiv-10 DocBERT Accuracy 0.764 #3 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.

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