Papers › Deep Biaffine Attention for Neural Dependency Parsing

Deep Biaffine Attention for Neural Dependency Parsing

6 Nov 2016arXiv:1611.01734archive 2025-07-28

Timothy Dozat, Christopher D. Manning

This paper builds off recent work from Kiperwasser & Goldberg (2016) using neural attention in a simple graph-based dependency parser. We use a larger but more thoroughly regularized parser than other recent BiLSTM-based approaches, with biaffine classifiers to predict arcs and labels. Our parser gets state of the art or near state of the art performance on standard treebanks for six different languages, achieving 95.7% UAS and 94.1% LAS on the most popular English PTB dataset. This makes it the highest-performing graph-based parser on this benchmark---outperforming Kiperwasser Goldberg (2016) by 1.8% and 2.2%---and comparable to the highest performing transition-based parser (Kuncoro et al., 2016), which achieves 95.8% UAS and 94.6% LAS. We also show which hyperparameter choices had a significant effect on parsing accuracy, allowing us to achieve large gains over other graph-based approaches.

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="1611.01734")

Code

Syntology Ran 3 of 19 code samples harvested from 6 repositories linked to this paper; 16 have no recorded run. Of those that ran: 1 ran · violated contract; 1 ran · our draft was wrong; 1 ran · fixture could not drive it.

By repository: community (archive-listed): 19 samples from 6 repositories, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

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

FranxYao/PoincareProbe mentioned on GitHubpytorch report
ShannonAI/mrc-for-dependency-parsing mentioned on GitHubpytorchApache-2.0 report
XuezheMax/NeuroNLP2 mentioned on GitHubpytorchGPL-3.0 report
anaezquerro/separ mentioned on GitHubpytorchApache-2.0 report
baidu/DDParser mentioned on GitHubpaddleApache-2.0 report
chantera/biaffineparser mentioned on GitHubpytorchApache-2.0 report
danifg/SyntacticPointer mentioned on GitHubpytorchGPL-3.0 report
deepdialog/tf-parser mentioned on GitHubtf report
fajri91/NeuralRST-TopDown mentioned on GitHubpytorch report
fajri91/RSTExtractor mentioned on GitHubpytorch report
februa22/biaffineparser mentioned on GitHubpytorchGPL-3.0 report
freesunshine0316/dep-forest-re mentioned on GitHubtf report
ganeshjawahar/ELMoLex mentioned on GitHubpytorchGPL-3.0 report
idiap/g2g-transformer mentioned on GitHubpytorchGPL-2.0 report
makyr90/Biaffine_Parser mentioned on GitHubpytorch report
mgzeke0/biaffineparser mentioned on GitHubpytorchGPL-3.0 report
redrew/neuralrst-bottom-up mentioned on GitHubpytorch report
shitian-taiger/relational-extraction mentioned on GitHubpytorch report
tdozat/Parser mentioned on GitHubtfApache-2.0 report
tdozat/Parser-v1 mentioned on GitHubtfApache-2.0 report
vsubramaniam851/typ_embed mentioned on GitHubpytorch report
wanghm92/Sing_Par mentioned on GitHubtfMIT report
yzhangcs/parser mentioned on GitHubpytorchMIT report
dmlc/gluon-nlp mxnetApache-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

19 samples harvested; 3 ran; 0 honoured the contract we drafted; 16 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 · violated contract
1ran · our draft was wrong
1ran · fixture could not drive it
16unverified

Licence: 2 of the 19 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 6 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.

get_num_other_elem redrew/neuralrst-bottom-up/models/architecture/bottom_up_architecture.py community (archive-listed) ran · fixture could not drive it no licence file found · pointer only · 73d6747bfa5543ce · report
is_number JoesSattes/Thai-Biaffine-Dependency-Parsing/preprocess.py community (archive-listed) ran · violated contract MIT (permissive) · 1889abe3c29f3531 · report
set_label_action redrew/neuralrst-bottom-up/train_rst_parser.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · 06e98e0817b9c50f · report
add_docstring baidu/DDParser/ddparser/ernie/file_utils.py community (archive-listed) unverified Apache-2.0 (permissive) · 35a97b86a05fcd5c · report
append_name baidu/DDParser/ddparser/ernie/modeling_ernie.py community (archive-listed) unverified Apache-2.0 (permissive) · 57d3f2c264025939 · report
categorical_accuracy chantera/biaffineparser/src/models.py community (archive-listed) unverified Apache-2.0 (permissive) · 4cb6893c39bb6390 · report
chuliu_edmonds chantera/biaffineparser/src/utils/chuliu_edmonds.py community (archive-listed) unverified Apache-2.0 (permissive) · 906bfaff2c598764 · report
chuliu_edmonds_one_root chantera/biaffineparser/src/utils/chuliu_edmonds.py community (archive-listed) unverified Apache-2.0 (permissive) · f209dc6a414e163b · report
collate chantera/biaffineparser/src/data.py community (archive-listed) unverified Apache-2.0 (permissive) · fff6c1cc919ef43f · report
evaluate chantera/biaffineparser/src/utils/conll.py community (archive-listed) unverified Apache-2.0 (permissive) · 75843fe2dd997b53 · report
forward chantera/biaffineparser/src/training.py community (archive-listed) unverified Apache-2.0 (permissive) · 2a8f48dd9ad2f576 · report
load_embeddings chantera/biaffineparser/src/utils/data.py community (archive-listed) unverified Apache-2.0 (permissive) · d9f663d6651746c4 · report
orthonormal_initializer tdozat/Parser/lib/linalg.py community (archive-listed) unverified Apache-2.0 (permissive) · 2e71814e529d090b · report
orthonormal_initializer wanghm92/Sing_Par/lib/linalg.py community (archive-listed) unverified MIT (permissive) · 90d46b3cd3eacbaf · report
parse_conll chantera/biaffineparser/src/utils/conll.py community (archive-listed) unverified Apache-2.0 (permissive) · d9eca1a4508f789e · report
sigmoid tdozat/Parser/lib/linalg.py community (archive-listed) unverified Apache-2.0 (permissive) · 5ee5f3de417ac23d · report
smooth wanghm92/Sing_Par/lib/etc/smooth.py community (archive-listed) unverified MIT (permissive) · 0073d56ba1481305 · report
tanh tdozat/Parser/lib/linalg.py community (archive-listed) unverified Apache-2.0 (permissive) · 00edc2dc619cd019 · report
tarjan chantera/biaffineparser/src/utils/chuliu_edmonds.py community (archive-listed) unverified Apache-2.0 (permissive) · 02240c2030c902b7 · report

Tasks

Dependency Parsing

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Dependency Parsing CoNLL-2009 Biaffine Parser LAS 85.38 #2 of 2 Archive leaderboard report
Dependency Parsing CoNLL-2009 Biaffine Parser UAS 88.90 #2 of 2 Archive leaderboard report
Dependency Parsing Penn Treebank Deep Biaffine + RoBERTa LAS 95.75 #4 of 22 Archive leaderboard report
Dependency Parsing Penn Treebank Deep Biaffine + RoBERTa UAS 97.29 #4 of 22 Archive leaderboard report
Dependency Parsing Penn Treebank Deep Biaffine LAS 94.22 #13 of 22 Archive leaderboard report
Dependency Parsing Penn Treebank Deep Biaffine UAS 95.87 #13 of 22 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.

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