no code implementations • 28 Nov 2023 • Ali H. Dhanaliwala, Rikhiya Ghosh, Sanjeev Kumar Karn, Poikavila Ullaskrishnan, Oladimeji Farri, Dorin Comaniciu, Charles E. Kahn
F1 score for extraction was 97% for RadLing-based system and 78% for GPT-4 system.
no code implementations • 5 Jun 2023 • Sanjeev Kumar Karn, Rikhiya Ghosh, Kusuma P, Oladimeji Farri
Instruction-tuned generative Large language models (LLMs) like ChatGPT and Bloomz possess excellent generalization abilities, but they face limitations in understanding radiology reports, particularly in the task of generating the IMPRESSIONS section from the FINDINGS section.
no code implementations • 4 Jun 2023 • Rikhiya Ghosh, Sanjeev Kumar Karn, Manuela Daniela Danu, Larisa Micu, Ramya Vunikili, Oladimeji Farri
Most natural language tasks in the radiology domain use language models pre-trained on biomedical corpus.
no code implementations • 7 Dec 2018 • Naveen Sundar Govindarajulu, Selmer Bringsjord, Rikhiya Ghosh
We begin to address this by presenting an embryonic formalization of a key part of any virtue-ethics theory: namely, the learning of virtue by a focus on exemplars of moral virtue.
no code implementations • 20 May 2018 • Naveen Sundar Govindarajulu, Selmer Bringjsord, Rikhiya Ghosh
Given that there exist many different formal and precise treatments of deontologi- cal and consequentialist ethics, we turn to virtue ethics and consider what could be a formalization of virtue ethics that makes it amenable to automation.