LAS: 80.01UAS: 85.24
Papers with Code · CC BY-SA 4.0
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).
논문
LAS: 81.37UAS: 86.05
F1: 92.46
Macro-averaged F1: 87.06
Labelled Attachment Score: 79.39Unlabeled Attachment Score: 83.82
UAS: 97.2LAS: 95.8
Labelled Attachment Score: 83.4Unlabeled Attachment Score: 87.2
UAS: 90.85LAS: 88.44
LAS: 85.38UAS: 88.90
LAS: 86.52UAS: 89.63
UAS: 97.30LAS: 95.92
LAS: 84.60UAS: 87.64
F1: 92.84
Labelled Attachment Score: 79.4Unlabeled Attachment Score: 83.4
POS: 97.3UAS: 97.42LAS: 96.26
LAS: 91.69UAS: 92.78
Macro F1: 81.13
Towards Better UD Parsing: Deep Contextualized Word Embeddings, Ensemble, and Treebank Concatenation
LAS: 75.84
LAS: 73.28UAS: 60.99BLEX: 66.09
LAS: 73.11UAS: 61.25BLEX: 64.49
LAS: 74.16UAS: 62.08BLEX: 65.28