The BE Seminar Series continues this week with two lectures delivered by our current PhD Students. We hope to see you there!
Date: November 15, 2018
Location: Room 337, Towne Building
Claim Extraction for Biomedical Publications
Speaker: Titipat Achikulvisut, Ph.D. Student
Advisor: Konrad Kording, Ph.D.
Time: 12:05-12:25 pm
Abstract:
Scientific claims are a foundation of scientific discourse. Extracting claims from scientific articles is primarily done by researchers during literature review and discussions. The enormous growth in scientific articles makes this ever more challenging and time-consuming. Here, we develop a deep neural network architecture to solve the problem. Our model an F1 score of 0.704 on a large corpus of expertly annotated claims within abstracts. Our results suggest that we can use a small dataset of annotated resources to achieve high-accuracy claim detection. We release a tool for discourse and claim detection, and a novel dataset annotated by experts. We discuss further applications beyond Biomedical literature.
Multiple Sclerosis Lesion Segmentation with Joint Label Fusion Evaluated on OASIS and CNN
Speaker: Mengjin Dong, Ph.D. Student
Advisor: Paul Yushkevich, Ph.D.
Time: 12:30-12:50 pm
Abstract:
Scientific claims are a foundation of scientific discourse. Extracting claims from scientific articles is primarily done by researchers during literature review and discussions. The enormous growth in scientific articles makes this ever more challenging and time-consuming. Here, we develop a deep neural network architecture to solve the problem. Our model an F1 score of 0.704 on a large corpus of expertly annotated claims within abstracts. Our results suggest that we can use a small dataset of annotated resources to achieve high-accuracy claim detection. We release a tool for discourse and claim detection, and a novel dataset annotated by experts. We discuss further applications beyond Biomedical literature.