Please Mind the Root: Decoding Arborescences for Dependency Parsing
EMNLP 2020, pp. 4809-4819, 2020.
The connection between dependency trees and spanning trees is exploited by the NLP community to train and to decode graph-based dependency parsers. However, the NLP literature has missed an important difference between the two structures: only one edge may emanate from the root in a dependency tree. We analyzed the output of state-of-the-...More
PPT (Upload PPT)