Riddle Generation using Word Associations

Riddle Generation using Word Associations Paloma Galv´an1, Virginia Francisco1, Raquel Herv´as1, Gonzalo M´endez2 1Departamento de Ingenier´ıa del Software e Inteligencia Artificial 2Instituto de Tecnolog´ıa del Conocimiento Universidad Complutense de Madrid, Spain palomagalvan@ucm.es, {virginia,raquelhb,gmendez}@fdi.ucm.es Abstract In knowledge bases where concepts have associated properties, there is a large amount of comparative information that is implicitly encoded in the values of the properties these concepts share. Although there have been previous approaches to generating riddles, none of them seem to take advantage of structured information stored in knowledge bases such as Thesaurus Rex, which organizes concepts according to the fine grained ad-hoc categories they are placed into by speakers in everyday language, along with associated properties or modifiers. Taking advantage of these shared properties, we have developed a riddle generator that creates riddles about concepts represented as common nouns. The base of these riddles are comparisons between the target concept and other entities that share some of its properties. In this paper, we describe the process we have followed to generate the riddles starting from the target concept and we show the results of the first evaluation we have carried out to test the quality of the resulting riddles. Keywords: Computational Creativity, Riddle Generation, Word Associations 1. Introduction In knowledge bases where concepts have associated prop- erties, there is a large amount of comparative information that is implicitly encoded in the values of the properties that these concepts share. This kind of information can be use- ful in tasks where it is required to automatically establish relations between concepts, such as the generation of com- parisons between entities based on shared properties (e.g. this shirt is as white as snow). These tasks are included in computational creativity, trying to simulate the natural behaviour of human beings to be creative using computer programs. In this paper we present a riddle generator that creates rid- dles about concepts represented as common nouns. The base of these riddles are comparisons between the target concept (i.e. a shirt) and other entities that share some of its properties (i.e. snow). The resulting riddles are com- posed as a sequence of comparisons following this tem- plate: “What is. . . as attribute as concept?”, where attribute is a property of the target concept which is the answer to the riddle, and concept is a different entity that shares the value of the attribute with the target concept. For exam- ple, “What is. . . as hard as concrete and as transparent as hair?” is a riddle generated for the concept diamond by the riddle generator. In order to gather information about the features that char- acterize the target concept of the riddle, and to obtain sim- ilar concepts according to those features, a word associa- tion resource called Thesaurus Rex (Veale and Li, 2013) has been used. This paper is organized as follows. Section 2 provides a overview of the state of the art of riddle and puzzle gener- ation. Section 3 explains our approach to generate riddles using …

Content truncated to 500 words