Learn More
— Support vector machines are a valuable tool for making classifications, but their black-box nature means that they lack the natural explanatory value that many other classifiers possess. Alternatively, many popular websites have shown recent success in explaining recommendations based on behavior of other users. Inspired by these ideas, we suggest two(More)
Social networks support efficient decentralized search: people can collectively construct short paths to a specified target in the network. Rank-based friendship—where the probability that person u befriends person v is inversely proportional to the number of people who are closer to u than v is—is an empirically validated model of acquaintanceship that(More)
One challenge faced by cognitive systems is how to organize information that is learned by reading. Analogical reasoning provides a method for immediately using learned knowledge, and analogical generalization potentially provides a means to integrate knowledge across multiple sources. To use analogy requires organizing information into effective cases.(More)
Word sense disambiguation is an important problem in learning by reading. This paper introduces analogical word-sense disambiguation, which uses human-like analogical processing over structured, relational representations to perform word sense disambiguation. Cases are automatically constructed using representations produced via natural language analysis of(More)
ii Introduction It has been a long term vision of Artificial Intelligence to develop Learning by Reading systems that can capture knowledge from naturally occurring texts, convert it into a deep logical notation and perform some inferences/reasoning on them. Such systems directly build on relatively mature areas of research, including Information Extraction(More)
One of the original motivations for qualitative reasoning was to capture the informal, intuitive notions about the continuous world that we all share, learned via a combination of experience and culture. For example, prior research suggests that qualitative dynamics can play an important role in natural language semantics. However, the constraints of(More)
Support vector machines are valuable for making classifications, but they lack the natural explanatory capability that many other classifiers possess. We suggest two methods for providing insight into support vector machine classifications. In the first, we report the support vectors most influential in the final classification for a particular test point.(More)
  • 1