Dependency Parsing
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).
Papers
Showing 1–10 of 1407 papers
All datasetsPenn TreebankUniversal DependenciesGENIA - LASGENIA - UASTweebankCoNLL-2009French GSDParTUTSequoia TreebankSpoken CorpusChinese TreebankDaNE
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | UDPipe 2.0 + mBERT + FLAIR | LAS | 84.6 | — | Unverified |
| 2 | UDify | LAS | 80.43 | — | Unverified |
| 3 | HIT-SCIR | LAS | 75.84 | — | Unverified |
| 4 | Stanford+ | LAS | 74.16 | — | Unverified |
| 5 | TurkuNLP | LAS | 73.28 | — | Unverified |
| 6 | UDPipe 2.0 | LAS | 73.11 | — | Unverified |