Transition-based Natural Language Processing
Transition-based models use a transition system, or abstract state machine, to model structured prediction problems, for example syntactic dependency parsing, as a sequence of actions. We propose a technique for learning representations of these states.…
SpatialHadoop: A MapReduce Framework for Big Spatial Data
This talk describes SpatialHadoop; an open-source full-fledged system for indexing, querying, and visualizing big spatial data. SpatialHadoop is built as a comprehensive extension to Hadoop that injects spatial data awareness inside each Hadoop layer, namely,…
Opening the world of advanced software technology
By Judith Bishop, Director of Computer Science, Microsoft Research In the world of information technology, the word “open” can mean many different things. For me, it refers to how software is both written and used,…
On fusing recursive traversals of K-d trees
IEEE Computer Society honors Wolfram Schulte for research leadership, contributions to program verification
By George Thomas Jr., Writer, Microsoft Software verification — the crucial process of assuring programs perform as expected — may not be top of mind for most of us. But considering its role in the…