On the Design of an Artificial Player for a Popular Word Game

This paper describes the design of an implemented software system intended to accomplish a specific natural language processing task. The targeted task is a challenge of the Evaluation Campaign of Natural Language Processing and Speech Tools for Italian proposed in 2020. The challenge is to design and implement an artificial player for the closing game of a popular Italian television show. Given five words, the goal of the player is to find a word related to, but also different from, the given words. The design of the proposed artificial player is discussed by presenting the dataset used to acquire sufficient linguistic knowledge and by briefly describing the algorithm used to play the game. A preliminary experimental evaluation of the artificial player is also discussed.