Talk: Biomedical Relation Extraction (Roland Roller, 2015/01/28)

Speaker: Roland Roller

Currently I am a 3rd year PhD student at the University of Sheffield. Before, I studied Computer Science and Computational Linguistics at the University of Trier and Saarland University in Germany. After graduation I worked as a software engineer at the German Research Center for Artificial Intelligence (DFKI). Right now I am visiting your research group for four weeks.

Data: January 28th 2015, Wednesday
Time: 17:00
Room: 3.2 room. Faculty of Informatics (UPV/EHU)

Title: “Biomedical Relation Extraction using Distant Supervision”

Abstract:

Automatic recognition of relationships between key entities in text is an
important task that has been used to identify useful relations such as
interactions between drugs and potential drug side-effects. Supervised
machine learning techniques have proved to be the most effective approach
to this problem. However, they require labelled training data which may not
be available in sufficient quantity (or at all) and is expensive to
produce. Distant supervision is an alternative technique trying to overcome
this problem by labelling large amounts of training data automatically
using known facts from a knowledge base. This talk will present first
results, ongoing research and challenges using distant supervision for
biomedical relation extraction.