Inspired by successes in computer vision, we tackle data drift by sequentially aligning learned representations. We evaluate on three challenging tasks varying ...

Jul 17, 2020 · Inspired by successes in computer vision, we tackle data drift by sequentially aligning learned representations. We evaluate on three ...

Johannes Bjerva, Wouter M. Kouw , Isabelle Augenstein: Back to the Future - Temporal Adaptation of Text Representations. AAAI 2020: 7440-7447.

In this paper, we apply a domain adaptation technique to correct for shifts. Domain adaptation is a furtive area of re- search within machine learning that ...

This type of temporal signal is typically overlooked, but is important if one aims to deploy a machine learning model over an extended period of time. In ...

Back to the future – temporal adaptation of text representations. J Bjerva, WM Kouw, I Augenstein. AAAI Conference on Artificial Intelligence 34 (5), 7440-7447, ...

May 13, 2024 · In this paper, we introduce the first task of explainable temporal reasoning, to predict an event's occurrence at a future timestamp based on context.

Self-labeling shows consistent improvement and notably, for named entity recognition, leads to better temporal adaptation than even human annotations, ...

Oct 26, 2021 · Johannes Bjerva, Wouter Kouw, and Isabelle Augenstein. Back to the future - temporal adaptation of text representations. In Proc. of AAAI, 2020.

Sep 7, 2022 · We study temporal effects on model performance on downstream language tasks, establishing a nuanced terminology for such discussion and identifying factors.