We exploit sketch techniques, especially the Count-Min sketch, a memory, and time efficient framework which approximates the frequency of a word pair in the corpus without explic...
Conversations provide rich opportunities for interactive, continuous learning. When something goes wrong, a system can ask for clarification, rewording, or otherwise redirect the...
We present a data-driven approach to generating responses to Twitter status posts, based on phrase-based Statistical Machine Translation. We find that mapping conversational stim...
This paper describes an algorithm for exact decoding of phrase-based translation models, based on Lagrangian relaxation. The method recovers exact solutions, with certificates of...
Accurate prediction of demographic attributes from social media and other informal online content is valuable for marketing, personalization, and legal investigation. This paper d...
John D. Burger, John C. Henderson, George Kim, Gui...