no code implementations • ACL (IWPT) 2021 • Stefan Grünewald, Annemarie Friedrich, Jonas Kuhn
We find that the choice of pre-trained embeddings has by far the greatest impact on parser performance and identify XLM-R as a robust choice across the languages in our study.
1 code implementation • EMNLP (LAW, DMR) 2021 • Teresa Bürkle, Stefan Grünewald, Annemarie Friedrich
In this paper, we present a first attempt at enriching German Universal Dependencies (UD) treebanks with enhanced dependencies.
no code implementations • ACL (IWPT) 2021 • Stefan Grünewald, Frederik Tobias Oertel, Annemarie Friedrich
This paper presents our multilingual dependency parsing system as used in the IWPT 2021 Shared Task on Parsing into Enhanced Universal Dependencies.
no code implementations • UDW (COLING) 2020 • Stefan Grünewald, Annemarie Friedrich
HDT-UD, the largest German UD treebank by a large margin, as well as the German-LIT treebank, currently do not analyze preposition-determiner contractions such as zum (= zu dem, “to the”) as multi-word tokens, which is inconsistent both with UD guidelines as well as other German UD corpora (GSD and PUD).
1 code implementation • 24 Oct 2023 • Timo Pierre Schrader, Matteo Finco, Stefan Grünewald, Felix Hildebrand, Annemarie Friedrich
Keeping track of all relevant recent publications and experimental results for a research area is a challenging task.
1 code implementation • 5 Jul 2023 • Timo Pierre Schrader, Teresa Bürkle, Sophie Henning, Sherry Tan, Matteo Finco, Stefan Grünewald, Maira Indrikova, Felix Hildebrand, Annemarie Friedrich
We present and release a new dataset of 50 manually annotated research articles.
1 code implementation • 14 Dec 2022 • Sophie Henning, Nicole Macher, Stefan Grünewald, Annemarie Friedrich
Modal verbs (e. g., "can", "should", or "must") occur highly frequently in scientific articles.
1 code implementation • CoNLL (EMNLP) 2021 • Elizaveta Sineva, Stefan Grünewald, Annemarie Friedrich, Jonas Kuhn
In this paper, we revisit the task of negation resolution, which includes the subtasks of cue detection (e. g. "not", "never") and scope resolution.
no code implementations • 15 Jun 2021 • Stefan Grünewald
Modern graph-based syntactic dependency parsers operate by predicting, for each token within a sentence, a probability distribution over its possible syntactic heads (i. e., all other tokens) and then extracting a maximum spanning tree from the resulting log-probabilities.
no code implementations • EACL 2021 • Stefan Grünewald, Prisca Piccirilli, Annemarie Friedrich
In this paper, we address the representation of coordinate constructions in Enhanced Universal Dependencies (UD), where relevant dependency links are propagated from conjunction heads to other conjuncts.
2 code implementations • 23 Oct 2020 • Stefan Grünewald, Annemarie Friedrich, Jonas Kuhn
We find that the choice of pre-trained embeddings has by far the greatest impact on parser performance and identify XLM-R as a robust choice across the languages in our study.
no code implementations • ACL 2018 • Stefan Grünewald, Sophie Henning, Alexander Koller
Chart constraints, which specify at which string positions a constituent may begin or end, have been shown to speed up chart parsers for PCFGs.