Towards Automatic Identification of Effective Clues for Team Word-Guessing Games

Towards Automatic Identification of Effective Clues for Team Word-Guessing Games Eli Pincus & David Traum USC Institute for Creative Technologies 12015 Waterfront Dr Playa Vista, CA 90094, USA pincus,traum @ict.usc.edu Abstract Team word-guessing games where one player, the clue-giver, gives clues attempting to elicit a target-word from another player, the receiver, are a popular form of entertainment and also used for educational purposes. Creating an engaging computational agent capable of emulating a talented human clue-giver in a timed word-guessing game depends on the ability to provide effective clues (clues able to elicit a correct guess from a human receiver). There are many available web resources and databases that can be mined for the raw material for clues for target-words; however, a large number of those clues are unlikely to be able to elicit a correct guess from a human guesser. In this paper, we propose a method for automatically filtering a clue corpus for effective clues for an arbitrary target-word from a larger set of potential clues, using machine learning on a set of features of the clues, including point-wise mutual information between a clue’s constituent words and a clue’s target-word. The results of the experiments significantly improve the average clue quality over previous approaches, and bring quality rates in-line with measures of human clue quality derived from a corpus of human-human interactions. The paper also introduces the data used to develop this method; audio recordings of people making guesses after having heard the clues being spoken by a synthesized voice (Pincus and Traum, 2016). Keywords: Word-Guessing Games, Clue-Giver, Clue, Guess, Point-Wise Mutual Information 1. Introduction Word-guessing games have a long history as a popular form of entertainment and have been created in many different forms. One kind of game is challenge games, where a moderator or opponent provides clues as a challenge to one or more guesser(s). Some forms of challenge games in- clude crossword puzzles, (first published in the newspaper, New York World in 1913), hangman, and twenty-questions, “college bowl” tournaments, and the TV show Jeopardy. Guessing games of this sort have also been used for peda- gogical purposes. Another type is team games, where the giver and receiver are both on the same team (possibly in competition with other teams), and the goal of the clue giver is not to chal- lenge the receiver(s) but to efficiently allow the receiver to guess the target. Generally, the clues are not allowed to con- tain any form of the target word the clue-giver is attempt- ing to elicit and there are time restrictions on how long the receiver has to make a correct guess. Parlor games such as Taboo and Catch-Phrase are examples of team-games. Peo- ple even enjoy watching others play these more interactive versions as evidenced by the popularity of television shows like Password and Pyramid. The fast-paced interactive na- ture of the dialogue that takes place in these games is chal- lenging for today’s dialogue systems to emulate. Skilled human clue-givers are able to rapidly select …

Content truncated to 500 words