Semantic integration focuses on discovering, representing, and manipulating correspondences between entities in disparate data sources. The topic has been widely studied in the context of structured data, with problems being considered including ontology and schema matching, matching relational tuples, and reconciling inconsistent data values. In recent years, however, semantic integration over text has also received increasing attention. This article studies a key challenge in semantic integration over text: identifying whether different mentions of real-world entities, such as "JFK" and "John Kennedy," within and across natural language text documents, actually represent the same concept. We present a machine-learning study of this problem.

Case-based reasoning (CBR) is becoming a viable real-world technology. First, it fragments each CBR system across many chapters, making it difficult to get the big picture of how the system works and obscuring the interrelatedness of the system's parts. In addition, having each chapter draw its examples from multiple systems adds a certain context-switching overhead: Each time a system is introduced (or reintroduced), the book must set the context anew, and the reader must recall the details of the system. A second drawback to the unified framework is that although it has fairly broad coverage, it is still biased toward those systems that fit it best. As a result, important work sometimes gets only a cursory mention in the book.

I am having a hard time making a machine suffer. Strengthening learning of a machine by giving it negative feedback is tricky. But then it is debatable if all humans learn alike from rewards/punishments:\ And that is why we stay enamored by kids. How do they learn what they learn? They never knew the language before; they never knew any of the concepts of this world before.

Hiding racy photos on your phone can be a tedious, manual affair. Depending on the app, you need to first select all the pics you want to move, move them and then delete them from your original cameral roll. That's not to mention making sure they didn't go to any automatic cloud backup locations like iCloud or Google Photos. A new app, Nude, aims to make the process a lot easier by scanning your photos for nudes, putting them in a private vault, deleting them from your camera roll and then erasing them from iCloud. All of this analysis is done on your iPhone, too, so no sensitive information hits the cloud.

Among the many properties ascribed to the magical number seven is that of marking out the significant epochs of a human life-span -- seven years from birth to departure from the kindergarten, another seven to puberty, another seven to majority. The occasion of the Seventh International Machine Intelligence Workshop is perhaps an appropriate moment to take stock. Views differ as to exactly which of the successive thresholds is the one on which machine intelligence research is now poised. But there is no mistaking the sense of transition, felt both by its practitioners, who claim that their field is at last attaining maturity, and in a rather different way by its interested Spectators. The latter rightly point out that if maturation brings opportunity and new powers it also brings the obligation to earn a living.