We present a novel framework for learning to interpret and generate language using only per- ceptual context as supervision. We demonstrate its capabilities by developing a system that learns to sportscast simulated robot soccer games in both English and Korean without any language-specific prior knowledge. Training employs only ambiguous supervision consisting of a stream of descrip- tive textual comments and a sequence of events extracted from the simulation trace. The system simultaneously establishes correspondences between individual comments and the events that they describe while building a translation model that supports both parsing and generation. We also present a novel algorithm for learning which events are worth describing. Human evaluations of the generated commentaries indicate they are of reasonable quality and in some cases even on par with those produced by humans for our limited domain.

Introduces voted perceptron. Compares with averaged perceptron, results similar. Large margin = voted or averaged? Poly kernel on mnist. Mnist separable if poly order >= 5. SVM achieves 1.1% err for d=4 poly kernel. Averaged perceptron achieves 1.5% err for d=3. After ~10 epochs regular perceptron also gets there but slower.