1 code implementation • 19 Jun 2023 • Matthias Hertel, Maximilian Beichter, Benedikt Heidrich, Oliver Neumann, Benjamin Schäfer, Ralf Mikut, Veit Hagenmeyer
We evaluate whether a Transformer load forecasting model benefits from a transfer learning strategy, where a global univariate model is trained on the load time series from multiple clients.
2 code implementations • 24 May 2023 • Hannah Bast, Matthias Hertel, Natalie Prange
We provide a more meaningful and fair in-depth evaluation of a variety of existing end-to-end entity linkers.
1 code implementation • 15 Aug 2022 • Hannah Bast, Matthias Hertel, Natalie Prange
We present Elevant, a tool for the fully automatic fine-grained evaluation of a set of entity linkers on a set of benchmarks.
2 code implementations • CoNLL (EMNLP) 2021 • Hannah Bast, Matthias Hertel, Mostafa M. Mohamed
We identify three key ingredients of high-quality tokenization repair, all missing from previous work: deep language models with a bidirectional component, training the models on text with spelling errors, and making use of the space information already present.