We present new results from a real-user evaluation of a data-driven approach to learning user-adaptive referring expression generation (REG) policies for spoken dialogue systems. ...
Current Referring Expression Generation algorithms rely on domain dependent preferences for both content selection and linguistic realization. We present two experiments showing t...
We present a data-driven approach to learn user-adaptive referring expression generation (REG) policies for spoken dialogue systems. Referring expressions can be difficult to unde...
This paper discusses the basic structures necessary for the generation of reference to objects in a visual scene. We construct a study designed to elicit naturalistic referring ex...
The generation of referring expressions (GRE), an important subtask of Natural Language Generation (NLG) is to generate phrases that uniquely identify domain entities. Until recen...