no code implementations • ACL (IWPT) 2021 • Mark Anderson, Carlos Gómez Rodríguez
We evaluate three leading dependency parser systems from different paradigms on a small yet diverse subset of languages in terms of their accuracy-efficiency Pareto front.
no code implementations • ACL (IWPT) 2021 • Mark Anderson, Mathieu Dehouck, Carlos Gómez Rodríguez
We evaluate the efficacy of predicted UPOS tags as input features for dependency parsers in lower resource settings to evaluate how treebank size affects the impact tagging accuracy has on parsing performance.
no code implementations • 1 Jun 2021 • Mark Anderson, Anders Søgaard, Carlos Gómez Rodríguez
S{\o}gaard (2020) obtained results suggesting the fraction of trees occurring in the test data isomorphic to trees in the training set accounts for a non-trivial variation in parser performance.