
Open access
Date
2020-11Type
- Conference Paper
ETH Bibliography
yes
Altmetrics
Abstract
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-art parsers on many languages from the Universal Dependency Treebank: although these parsers are often able to learn that trees which violate the constraint should be assigned lower probabilities, their ability to do so unsurprisingly de-grades as the size of the training set decreases.In fact, the worst constraint-violation rate we observe is 24%. Prior work has proposed an inefficient algorithm to enforce the constraint, which adds a factor of n to the decoding runtime. We adapt an algorithm due to Gabow and Tarjan (1984) to dependency parsing, which satisfies the constraint without compromising the original runtime. Show more
Permanent link
https://doi.org/10.3929/ethz-b-000462321Publication status
publishedExternal links
Book title
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)Pages / Article No.
Publisher
Association for Computational LinguisticsEvent
Organisational unit
09682 - Cotterell, Ryan / Cotterell, Ryan
Notes
Due to the Coronavirus (COVID-19) the conference was conducted virtually.More
Show all metadata
ETH Bibliography
yes
Altmetrics