2 papers
cs.CL2022
Heroes, Villains, and Victims, and GPT-3: Automated Extraction of Character Roles Without Training Data
Dominik Stammbach, Maria Antoniak, Elliott Ash
This paper shows how to use large-scale pre-trained language models to extract character roles from narrative texts without training data. Queried with a zero-shot question-answeri…
cs.CL2021
Evaluating Document Representations for Content-based Legal Literature Recommendations
Malte Ostendorff, Elliott Ash, Terry Ruas +3
Recommender systems assist legal professionals in finding relevant literature for supporting their case. Despite its importance for the profession, legal applications do not reflec…