Toward an interleaved model of actions and words in social simulation

  title={Toward an interleaved model of actions and words in social simulation},
  author={Jeff Orkin and D. Roy},
We present results of semi-automated annotation of dialogue data collected from 5, 200 gameplay logs from The Restaurant Game (, and show that classified dialogue acts can function effectively as a common currency for modeling behavior with interleaved physical actions and words. 
1 Citations
Dynamic NLP : A model for language bootstrapping and lifelong learning
This work argues the creation of larger multimodal multi-lingual corpora by proposing a dynamic approach to NLP that starts off by grounding on a set of sentences for which perceptual data and semantic maps are available, leading to a dynamic lexicon-syntax-semantics cycle. Expand


Automatic learning and generation of social behavior from collective human gameplay
Promising results are documents from the first iteration of a Collective Artificial Intelligence system that generates behavior and dialogue in real-time from data captured from over 11,000 players of The Restaurant Game. Expand
The Restaurant Game: Learning Social Behavior and Language from Thousands of Players Online
A methodology for unsupervised learning of a Plan Network using a multiplayer video game, visualization of this network, and evaluation of the learned model with respect to human judgment of typical behavior are described. Expand
Scripts, plans, goals and understanding: an inquiry into human knowledge structures
For both people and machines, each in their own way, there is a serious problem in common of making sense out of what they hear, see, or are told about the world. The conceptual apparatus necessaryExpand