Since speaker's intentions can be represented into domain actions (pairs of domain-independent speech acts and domain-dependent concept sequences) in goal-oriented dialogues,...
In this paper we describe two geometrical models of meaning representation, the Semantic Atlas (SA) and the Automatic Contexonym Organizing Model (ACOM). The SA provides maps of m...
A number of recent studies have demonstrated that groups benefit considerably from access to shared visual information. This is due, in part, to the communicative efficiencies pro...
Topic tracking is complicated when the stories in the stream occur in multiple languages. Typically, researchers have trained only English topic models because the training storie...
Leah S. Larkey, Fangfang Feng, Margaret E. Connell...
Vector-based models of lexical semantics retrieve semantically related words automatically from large corpora by exploiting the property that words with a similar meaning tend to ...