I am an Associate Professor in the Department of Computing Science, University of Alberta.
My research is on knowledge management, information retrieval, and natural language processing, and I work on machine learning methods applied to these fields. I have supervised graduate level research on the problems of named entity recognition, typing and disambiguation; open relation extraction; understanding social processes in Wikipedia article authoring; mining citation networks; and semistructured data management.
I am passionate about Linked Open Data, and I work with Digital Humanities colleagues on creating, indexing, and processing knowledge graphs out of heritage, cultural, scholarly, and literary work. I am a co-PI within LINCS -- Linked Open Data for Canadian Cultural Research.
I teach databases, natural language processing, and information retrieval.
My slides for an undergraduate Database Management Systems course are now open sourced.
I serve as Vice-President of CAIAC -- the Canadian Artificial Intelligence Association and as an Associate Editor of the Distributed and Parallel Databases (DAPD).
Occasionally, I serve as a reviewer for ACM Computing Reviews.
My students and I contribute often open source research code. Some recent projects:
- EXEMPLAR (Relation Extraction)
- WNED (Named Entity Disambiguation)
- HRERE (Heterogeneous Representations for Neural Relation Extraction) SOTA as of NAACL 2019
- NFETC (Neural Fine-Grained Entity Type Classification)
- PRIMA (IR on the Internet archive)
- LECTOR+ (information extraction from Wikipedia)
I am thrilled to count on generous support for my research from Diffbot.
in person: Office: ATH 4-51