An Empirical Investigation of Structured Output Modeling for Graph-based Neural Dependency Parsing
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F19%3A10427132" target="_blank" >RIV/00216208:11320/19:10427132 - isvavai.cz</a>
Result on the web
<a href="https://www.aclweb.org/anthology/P19-1562" target="_blank" >https://www.aclweb.org/anthology/P19-1562</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
An Empirical Investigation of Structured Output Modeling for Graph-based Neural Dependency Parsing
Original language description
In this paper, we investigate the aspect of structured output modeling for the state-of-the-art graph-based neural dependency parser (Dozat and Manning, 2017). With evaluations on 14 treebanks, we empirically show that global output-structured models can generally obtain better performance, especially on the metric of sentence-level Complete Match. However, probably because neural models already learn good global views of the inputs, the improvement brought by structured output modeling is modest.
Czech name
—
Czech description
—
Classification
Type
O - Miscellaneous
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
—
Others
Publication year
2019
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů