Generating and interpreting referring expressions in context
Dustin Smith · 2013
Doctor of Philosophy Referring expressions with vague and ambiguous modiers, such as “a quick visit ” and “the big meeting, ” are dicult for computers to interpret because their meanings are dened in part by context. For the hearer to arrive at the speaker’s intended meaning, he must consider the alternative decisions that the speaker was faced with in context. To address these challenges, I propose a new approach to both generating and interpreting referring expressions based on belief-state planning and plan recognition. Planning in belief space oers a way to capture referential uncertainty and the incremental nature of generating and interpretation, because each belief state represents a complete interpretation. The contributions of my thesis are as follows: (1) A computational model of reference generation and interpretation that is fast, incremental, and non-deterministic. This model includes a lexical semantics for a fragment of English noun phrases, which species the encoded meanings of determiners (quantiers and articles), gradable and ambiguous modiers. It performs in real time, even when the hypothesis space grows very