Mining Big Biomedical Text: Discovering Publicly Unknown Knowledge from PubMed
Date: March 27, 2015
Time: 12:30pm – 1:30pm
Room: Wells Library, Rm LI 030
The enormous amount of biomedicine’s natural-language texts creates a daunting challenge to discover novel and interesting patterns embedded in the text corpora that help biomedical professionals find new drugs and treatments. These patterns constitute entities such as genes, compounds, treatments, and side effects and their associations that spread across publications in different biomedical specialties. In this talk, I propose a new bio text mining system, called bio-Spuri, to discover previously unknown relations in biomedical text. Bio-Spuri is designed to overcome the problems of Swanson’s ABC model by using semantic path analysis to tell a story about plausible connections between biological terms. It consists of two major components: extraction and inference. In extraction process, bio entity and relation are identified by extending Stanford core NLP. In inference process, storytelling-based semantic path analysis is conducted to spot relation of bio-entities that are semantically close to each other, and reveals insight into how a series of entity pairs is organized, and how it can be harnessed to explain seemingly unrelated connections. At the end of my talk, I introduce several applications employing bio-Spuri and talk about the future direction of bio text mining.
Min Song is the Underwood Distinguished Professor in the Department of Library and Information Science and the director of Text and Social Media Mining Lab at Yonsei University. Prior to Yonsei, he was an Associate Professor in the Department of Information Systems at New Jersey Institute of Technology. Min received the best paper award from EDB in 2013, the outstanding service award from CIKM in 2009. His work received an honorable mention award in the 2006 Greater Philadelphia Bioinformatics Symposium and the Drexel Best Dissertation Award in 2005. He has published 1 book, 8 book chapters, 50 international journals, and 70 conference papers. Min has research interests in Biomedical Text Mining, Social Media Data Mining, and Information Retrieval. He received his PhD in Information Systems from Drexel University, a MA from Indiana University and a BA from Yonsei University in Korea.