End-user scripting languages are relatively easy to learn, but have limited expressive power. Tile-based scripting systems are particularly accessible to beginners, but usually ar...
Many researchers are trying to use information extraction (IE) to create large-scale knowledge bases from natural language text on the Web. However, the primary approach (supervis...
Much of the work done in the field of tangible interaction has focused on creating tools for learning; however, in many cases, little evidence has been provided that tangible inte...
Michael S. Horn, Erin Treacy Solovey, R. Jordan Cr...
We present a probabilistic generative model for learning semantic parsers from ambiguous supervision. Our approach learns from natural language sentences paired with world states ...
In this paper, we present a reinforcement learning approach for mapping natural language instructions to sequences of executable actions. We assume access to a reward function tha...
S. R. K. Branavan, Harr Chen, Luke S. Zettlemoyer,...