We built a system for the automatic creation of a textbased topic hierarchy, meant to be used in a geographically defined community. This poses two main problems. First, the appea...
Clustering by document concepts is a powerful way of retrieving information from a large number of documents. This task in general does not make any assumption on the data distrib...
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...
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. ...
Previous work has shown that high quality phrasal paraphrases can be extracted from bilingual parallel corpora. However, it is not clear whether bitexts are an appropriate resourc...
Juri Ganitkevitch, Chris Callison-Burch, Courtney ...