Cruciform: Solving Crosswords with Natural Language Processing

TL;DR

Cruciform is a novel crossword solving system that integrates natural language processing components with constraint satisfaction techniques to effectively solve puzzles, handling nuanced clues and grid constraints.

Contribution

This paper introduces Cruciform, a new system combining NLP and constraint satisfaction for crossword solving, advancing beyond previous approaches like Dr. Fill.

Findings

Achieved improved accuracy in solving complex clues

Demonstrated effective integration of NLP components with grid constraints

Showed promising results in experimental evaluations

Abstract

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.