The Interplay Between Loss Functions and Structural Constraints in Dependency Parsing
Dependency parsing can be cast as a combinatorial optimization problem with the objective to find the highest-scoring graph, where edge scores are learnt from data. Several of the decoding algorithms that have been applied to this task employ structural restrictions on candidate solutions, such as...
Saved in:
Main Authors: | Robin Kurtz, Marco Kuhlmann |
---|---|
Format: | Article |
Language: | English |
Published: |
Linköping University Electronic Press
2019-12-01
|
Series: | Northern European Journal of Language Technology |
Online Access: | https://nejlt.ep.liu.se/article/view/1037 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Transition-Based Techniques for Non-Projective Dependency Parsing
by: Marco Kuhlmann, et al.
Published: (2010-10-01) -
Statistical Learning for Semantic Parsing: A Survey
by: Qile Zhu, et al.
Published: (2019-12-01) -
Parsing the heterogeneity of depression: a data-driven subgroup derived from cognitive function
by: Chenyang Xu, et al.
Published: (2025-01-01) -
Recursive Neural Networks Based on PSO for Image Parsing
by: Guo-Rong Cai, et al.
Published: (2013-01-01) -
Chinese Unknown Word Recognition for PCFG-LA Parsing
by: Qiuping Huang, et al.
Published: (2014-01-01)