The subject of this demonstration is natural language interaction, focusing on adaptivity and profiling of the dialogue management and the generated output (text and speech). Thes...
The GIVE Challenge is a new Internetbased evaluation effort for natural language generation systems. In this paper, we motivate and describe the software infrastructure that we de...
Alexander Koller, Donna Byron, Justine Cassell, Ro...
We compare the phenomena of clausal coordinate ellipsis in Estonian, a Finno-Ugric language, and German, an Indo-European language. The rules underlying these phenomena appear to ...
We present the results of a large-scale, end-to-end human evaluation of various sentiment summarization models. The evaluation shows that users have a strong preference for summar...
Kevin Lerman, Sasha Blair-Goldensohn, Ryan T. McDo...