Abstract. Recently it was shown that existing general-purpose inductive logic programming systems are useful for learning wrappers (known as L-wrappers) to extract data from HTML d...
We propose reliable outdoor object detection on mobile phone imagery from off-the-shelf devices. With the goal to provide both robust object detection and reduction of computation...
Our KNOWITALL system aims to automate the tedious process of extracting large collections of facts (e.g., names of scientists or politicians) from the Web in an autonomous, domain...
Oren Etzioni, Michael J. Cafarella, Doug Downey, A...
We argue that groups of unannotated texts with overlapping and non-contradictory semantics represent a valuable source of information for learning semantic representations. A simp...
We present a simple algorithm for clustering semantic patterns based on distributional similarity and use cluster memberships to guide semi-supervised pattern discovery. We apply ...