Modeling the clarification potential of instructions: Predicting clarification requests and other reactions

Luciana Benotti, Patrick Blackburn

Abstract: Highlights • We hypothesize that implicatures are a rich source of clarification requests. • We motivate the hypothesis in theoretical, practical and empirical terms. • We model clarification potential by inferring conversational implicatures. • Much of the inference can be handled using classical AI planning. • Discourse structure emerges as task structure is exploited opportunistically. Abstract We hypothesize that conversational implicatures are a rich source of clarification requests, and in this paper we do two things. First, we motivate the hypothesis in theoretical, practical and empirical terms and formulate it as a concrete clarification potential principle: implicatures may become explicit as fourth-level clarification requests. Second, we present a framework for generating the clarification potential of an instruction by inferring its conversational implicatures with respect to a particular context. We evaluate the framework and illustrate its performance using a human–human corpus of situated conversations. Much of the inference required can be handled using classical planning, though as we shall note, other forms of means-ends analysis are also required. Our framework leads us to view discourse structure as emerging via opportunistic responses to task structure.