Cruciform: Solving Crosswords with Natural Language Processing
This work addresses the challenge of crossword solving for AI systems, but it is incremental as it builds on prior methods like Dr. Fill.
The authors tackled the problem of solving crossword puzzles by developing Cruciform, a system that combines natural language processing components to generate candidate answers from clues and uses grid constraints to solve the puzzle, achieving results comparable to existing systems like Dr. Fill.
Crossword puzzles are popular word games that require not only a large vocabulary, but also a broad knowledge of topics. Answering each clue is a natural language task on its own as many clues contain nuances, puns, or counter-intuitive word definitions. Additionally, it can be extremely difficult to ascertain definitive answers without the constraints of the crossword grid itself. This task is challenging for both humans and computers. We describe here a new crossword solving system, Cruciform. We employ a group of natural language components, each of which returns a list of candidate words with scores when given a clue. These lists are used in conjunction with the fill intersections in the puzzle grid to formulate a constraint satisfaction problem, in a manner similar to the one used in the Dr. Fill system. We describe the results of several of our experiments with the system.