Experience
Education
Bio
I am a researcher at Microsoft Research in Redmond, WA. My research interest is in advancing machine learning and natural language processing to automate discovery in genomics and precision medicine. My most recent work focuses on scaling semantic parsing to PubMed for extracting biological pathways, and on developing probabilistic methods to integrate pathways with high-throughput genomics data for cancer systems biology. I have received Best Paper Awards in NAACL, EMNLP, and UAI. Check out Literome, an Azure-based cloud service for automatically curating knowledge from PubMed. Currently, it focuses on two types of knowledge more pertinent to genomic medicine: gene-gene interactions (as in biological pathways) and genotype-phenotype associations, such as single nucleotide polymorphism (SNP) vs. disease predisposition or drug reaction [Bioinformatics Paper]. An overview of the overarching agenda can be found in this invited talk at NIPS-AKBC. I'm thrilled to join the DARPA Program on automating the construction of "Big Mechanisms" for cancer systems biology by reading literature, integrating ontologies and knowledgebases, and deciphering experimental data. I am a co-PI in a team led by Andrey Rzhetsky. I spent some truly amazing years in the Department of Computer Science and Engineering at the University of Washington. My Ph.D. advisor is Pedro Domingos. My dissertation is: Markov Logic for Machine Reading.