Most, but not all, of the clues and answers relate to AI. An answer may be an acronym or an abbreviation even though not noted in the clue. Some liberties have been taken, but only because the puzzle is meant to be fun and interesting. If you'd like a few answers, check out the "AI in the news" column on page 120. And for all of the answers, see the solution on page 116.
Now there's a better way to cheat at crossword puzzles--with artificial intelligence. Researchers from three universities designed a system that uses a type of AI known as deep learning to help computers understand language more quickly and effectively. As a bonus, the researchers built a web-based tool that's handy when a particularly baffling crossword clue comes around. The crossword assistant is just a demo of how deep learning is improving machines' ability to understand language, said Felix Hill, a Ph.D. candidate at the University of Cambridge and lead author of a paper describing the research. Learning language is challenging for computers because it's difficult to recreate the rich and diverse information sources available to humans when they learn to speak and read, he said.
The web-based system, developed by researchers from the UK, US and Canada, makes use of artificial neural networks, which are based on the brain's own learning systems. The researchers trained the system to understand words, phrases and sentences by feeding it hundreds of thousands of definitions of English words from six dictionaries, as well as Wikipedia. "Despite recent progress in AI, problems involving language understanding are particularly difficult," says Hill. "One of the biggest challenges in training computers to understand language is recreating the many rich and diverse information sources available to humans when they learn to speak and read."
The construction of a program that generates crossword puzzles is discussed. As in a recent paper by Dechter and Meiri, we make an experimental comparison of various search techniques. The conclusions to which we come differ from theirs in some areas - although we agree that directional arc consistency is better than path-consistency or other forms of lookahead, and that backjumping is to be preferred to backtracking, we disagree in that we believe dynamic ordering of the constraints to be necessary in the solution of more difficult problems.