Summary: Data-Driven Response Generation in Social Media
Computer Sci. & Eng.
University of Washington
Seattle, WA 98195
National Research Council Canada
Ottawa, Ontario, K1A 0R6
William B. Dolan
Redmond, WA 98052
We present a data-driven approach to generat-
ing responses to Twitter status posts, based on
phrase-based Statistical Machine Translation.
We find that mapping conversational stimuli
onto responses is more difficult than translat-