In this paper, we examine the problem of learning from noisecontaminated data in high-dimensional space. A new learning approach based on projections onto multi-dimensional ellips...
Analyzing spend transactions is essential to organizations for understanding their global procurement. Central to this analysis is the automated classification of these transacti...
The ways in which an agent’s actions affect the world can often be modeled compactly using a set of relational probabilistic planning rules. This paper addresses the problem of ...
Ashwin Deshpande, Brian Milch, Luke S. Zettlemoyer...
In order to respond correctly to a free form factual question given a large collection of texts, one needs to understand the question to a level that allows determining some of th...
The problem of acoustic-to-articulatory speech inversion continues to be a challenging research problem which significantly impacts automatic speech recognition robustness and ac...