no code implementations • RANLP 2017 • Daniel Dakota, S K{\"u}bler, ra
We investigate parsing replicability across 7 languages (and 8 treebanks), showing that choices concerning the use of grammatical functions in parsing or evaluation, the influence of the rare word threshold, as well as choices in test sentences and evaluation script options have considerable and often unexpected effects on parsing accuracies.
no code implementations • RANLP 2017 • Hai Hu, Daniel Dakota, S K{\"u}bler, ra
Parsing Chinese critically depends on correct word segmentation for the parser since incorrect segmentation inevitably causes incorrect parses.
no code implementations • RANLP 2019 • Kenneth Steimel, Daniel Dakota, Yue Chen, S K{\"u}bler, ra
Based on our findings, we can conclude that a multilingual optimization of classifiers is not possible even in settings where comparable data sets are used.
1 code implementation • ACL (IWPT) 2021 • Daniel Dakota, Zeeshan Ali Sayyed, Sandra Kübler
In order to determine towhat degree the data imbalance between two domains and the domain differences affect results, we also carry out an experiment with two imbalanced in-domain treebanks and show that loss weighting also improves performance in an in-domain setting.
no code implementations • EACL (AdaptNLP) 2021 • Daniel Dakota
We perform a systematic set of experiments using two neural constituency parsers to examine how different parsers behave in combination with different BERT models with varying source and target genres in English and Swedish.
no code implementations • COLING 2022 • Ludovic Mompelat, Daniel Dakota, Sandra Kübler
We investigate methods to develop a parser for Martinican Creole, a highly under-resourced language, using a French treebank.