Learn More
Lifestyle management is a growing area aimed at giving individuals support for an increased self-awareness; self-monitoring technologies are essential in providing an objective account of our daily events. However, most self-monitoring technological solutions largely focus on physical health and ignore other aspects. Our goal is to utilise context aware(More)
We have recently shown how to combine random walk inference over knowledge bases with vector space representations of surface forms, improving performance on knowledge base inference. In this paper, we formalize the connection of our prior work to logical inference rules, giving some general observations about methods for incorporating vector space(More)
Research Interests My research focuses on the intersection of computer vision and natural language processing and I am particularly interested in large-scale, data-driven algorithms for lifelong learning.
This experimental study investigated the relationship between the independent measures of font selection, type size, and type rendering technology and the dependent measures of legibility, as measured by the Chapman-Cook speed of reading test, as well as comprehension, as measured by a series of questions from the verbal comprehension section of the(More)
Previous accounts of the Canadian Shift, which have interpreted this diachronic process as a purely phonetic consequence of the low back LOT-THOUGHT vowel merger, have not clearly explained the strong connection between phonetic TRAP vowel retraction and the phonological process of the low back merger. This paper addresses this issue in several ways.(More)
Heavy tailed distributions present a tough setting for inference. They are also common in industrial applications, particularly with Internet transaction datasets, and machine learners often analyze such data without considering the biases and risks associated with the misuse of standard tools. This paper outlines a procedure for inference about the mean of(More)
  • 1