Automatic definition extraction and crosswords generation from news text

This paper describes the design and implementation of a system that takes Spanish text and generates crosswords (board and definitions) in a fully automatic way using the definitions extracted from those texts. Our solution divides the problem in two parts: a definition extraction module that applies pattern matching implemented in Python, and a crossword generation module that uses a greedy strategy implemented in Prolog. The system achieves 73% precision and builds crosswords similar to those built by humans.