Cryptic Crossword Clues: Generating Text with a Hidden Meaning

This paper discusses the generation of cryptic crossword clues: a task that involves generating texts that have both a surface reading, based on a natural language interpretation of the words, and a hidden meaning in which the strings that form the text can be interpreted as a puzzle. The process of clue generation realizes a representation of the hidden, puzzle meaning of the clue through the aggregation of chunks of text. As these chunks are combined, syntactic and semantic selectional constraints are explored, and through this language understanding task a meaningful surface reading is recovered. This hybrid language generation/language understanding process transforms a representation of the clue as a word puzzle into a representation of some meaningful assertion in the domain of the real world, mediated through the generated multi-layered text; a text which has two separate readings.