Self-training has been shown capable of improving on state-of-the-art parser performance (McClosky et al., 2006) despite the conventional wisdom on the matter and several studies ...
Abstract: This paper, entitled Challenges for the Protection of Critical ICTBased Financial Infrastructures for the next 5 years, will describe the outcomes of a recently held work...
Several NLP tasks are characterized by asymmetric data where one class label NONE, signifying the absence of any structure (named entity, coreference, relation, etc.) dominates al...
Many AI tasks can be formalized as constraint satisfaction problems (CSPs), which involve finding values for variables subject to a set of constraints. While solving a CSP is an ...
We present a new downsampling method for structured volume grids, which preserves much more of the topology of a scalar field than existing downsampling methods by preferably selec...