Delves into the 'digital turn' in history, examining historical research using digitized newspapers and exploring text reuse, word embeddings, and data visualization.
Emphasizes the importance of incompatibilities to prevent conflicts of interest and maintain democracy, advocating for a constitutional law on the matter.
Explores coreference resolution models, challenges in scoring spans, graph refinement techniques, state-of-the-art results, and the impact of pretrained Transformers.
Explores methods for information extraction, including traditional and embedding-based approaches, supervised learning, distant supervision, and taxonomy induction.
