In this paper we describe a new approach for learning dialog act processing. In this approach we integrate a symbolic semantic segmentation parse,: with a learning dialog act netw...
Conditional random field methods (CRFs) have gained popularity for image labeling tasks in recent years. In this paper, we describe an alternative discriminative approach, by exte...
Our goal is to build knowledge-based systems capable of answering a wide variety of questions, including questions that are unanticipated when the knowledge base is built. For sys...
The primary contribution of this paper is investigating how the User Centered Design approach is integrated into the industry. Employing a structured web-survey, targeted to the u...
We present a new approach for personalizing Web search results to a specific user. Ranking functions for Web search engines are typically trained by machine learning algorithms u...
David Sontag, Kevyn Collins-Thompson, Paul N. Benn...