| 1 |
Higher-order Derivatives of Weighted Finite-state Machines ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 4 |
Efficient computation of expectations under spanning tree distributions ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 5 |
Higher-order Derivatives of Weighted Finite-state Machines ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 6 |
On Finding the K-best Non-projective Dependency Trees
|
|
|
|
In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (2021)
|
|
BASE
|
|
Show details
|
|
|
| 7 |
Higher-order Derivatives of Weighted Finite-state Machines
|
|
|
|
In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (2021)
|
|
BASE
|
|
Show details
|
|
|
| 8 |
Efficient computation of expectations under spanning tree distributions
|
|
|
|
In: Transactions of the Association for Computational Linguistics, 9 (2021)
|
|
BASE
|
|
Show details
|
|
|
| 9 |
Efficient Sampling of Dependency Structure
|
|
|
|
In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (2021)
|
|
BASE
|
|
Show details
|
|
|
| 10 |
SIGMORPHON 2020 Shared Task 0: Typologically Diverse Morphological Inflection ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 13 |
Please Mind the Root: Decoding Arborescences for Dependency Parsing
|
|
|
|
In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) (2020)
|
|
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.
|
|
URL: https://doi.org/10.3929/ethz-b-000462321
https://hdl.handle.net/20.500.11850/462321
|
|
BASE
|
|
Hide details
|
|
|
| 14 |
Information-Theoretic Probing for Linguistic Structure
|
|
|
|
In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (2020)
|
|
BASE
|
|
Show details
|
|
|
|
|
