Browse State-of-the-Art › Dependency Parsing

Dependency Parsing

338 papers with code · 16 benchmarks · 15 datasets archive 2025-07-28

Natural Language Processing

Dependency parsing is the task of extracting a dependency parse of a sentence that represents its grammatical structure and defines the relationships between "head" words and words, which modify those heads.

Example:

     root
      |
      | +-------dobj---------+
      | |                    |
nsubj | |   +------det-----+ | +-----nmod------+
+--+  | |   |              | | |               |
|  |  | |   |      +-nmod-+| | |      +-case-+ |
+  |  + |   +      +      || + |      +      | |
I  prefer  the  morning   flight  through  Denver

Relations among the words are illustrated above the sentence with directed, labeled arcs from heads to dependents (+ indicates the dependent).

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

16 leaderboard tables shown for this task, 16 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 16 until expanded.

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
Penn Treebank (22 rows) Label Attention Layer + HPSG + XLNet Rethinking Self-Attention: Towards Interpretability in Neural Parsing code Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified Compare
Universal Dependencies (6 rows) UDPipe 2.0 + mBERT + FLAIR Evaluating Contextualized Embeddings on 54 Languages in POS... — — Compare
GENIA - LAS (3 rows) BiLSTM-CRF From POS tagging to dependency parsing for biomedical event extraction code — Compare
GENIA - UAS (3 rows) BiLSTM-CRF From POS tagging to dependency parsing for biomedical event extraction code — Compare
Tweebank (3 rows) SuPar-BERTweet Cross-Dialect Social Media Dependency Parsing for Social... code — Compare
CoNLL-2009 (2 rows) CRFPar Efficient Second-Order TreeCRF for Neural Dependency Parsing code Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified Compare
French GSD (2 rows) CamemBERT CamemBERT: a Tasty French Language Model code — Compare
ParTUT (2 rows) CamemBERT CamemBERT: a Tasty French Language Model code — Compare
Sequoia Treebank (2 rows) CamemBERT CamemBERT: a Tasty French Language Model code — Compare
Spoken Corpus (2 rows) CamemBERT CamemBERT: a Tasty French Language Model code — Compare
UD2.5 test (2 rows) Trankit Trankit: A Light-Weight Transformer-based Toolkit for Multilingual... code — Compare
100STLYE-Labelled (1 row) nlp The CMU METAL Farsi NLP Approach code — Compare
Chinese Treebank (1 row) MFVI Second-Order Neural Dependency Parsing with Message Passing and... code — Compare
DaNE (1 row) da_dacy_large_tft DaCy: A Unified Framework for Danish NLP — — Compare
NLPCC-2019 (1 row) CRFPar Efficient Second-Order TreeCRF for Neural Dependency Parsing code Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified Compare
Universal Dependency Treebank (1 row) Stanza Stanza: A Python Natural Language Processing Toolkit for Many... code Syntology community repositories only · 16 ran (of which 8 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 6 where Syntology's instrument failed) · 14 unverified Compare

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

15 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

5 subtasks in the archive's task tree.

Papers archive 2025-07-28

archive papers tagged: 1,407 · with a code link: 338 · where Syntology ran a sample: 36 (26 with a run with no instrument failure, 10 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (36 of 1,407 tagged: 26 with a run with no instrument failure, 10 where every run was a failure of Syntology's instrument)

Page 1 of 15: papers 1 to 100 of 1,407, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.

Syntology lines on 20 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

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