3 papers
cs.AI2025
Reduction of Supervision for Biomedical Knowledge Discovery
Christos Theodoropoulos, Andrei Catalin Coman, James Henderson +1
Knowledge discovery is hindered by the increasing volume of publications and the scarcity of extensive annotated data. To tackle the challenge of information overload, it is essent…
cs.CL2023
Transformers as Graph-to-Graph Models
James Henderson, Alireza Mohammadshahi, Andrei C. Coman +1
We argue that Transformers are essentially graph-to-graph models, with sequences just being a special case. Attention weights are functionally equivalent to graph edges. Our Graph-…
cs.CL2023
Strong and Efficient Baselines for Open Domain Conversational Question Answering
Andrei C. Coman, Gianni Barlacchi, Adrià de Gispert
Unlike the Open Domain Question Answering (ODQA) setting, the conversational (ODConvQA) domain has received limited attention when it comes to reevaluating baselines for both effic…